© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12625
    Prev
    Next
    INDEX
    Explanations

    references to the concept of length in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    occurrences of the word "length" in programming and scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    references to one-dimensional extent measurements, especially phrases stating the extent of something and code/math contexts that compute or discuss that extent.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the word "length" in technical or scientific contexts, particularly in code and mathematical expressions.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebServlet
    -0.63
     EARLY
    -0.50
    addGap
    -0.49
    ➟
    -0.47
    big
    -0.47
     big
    -0.47
    hoeddwyd
    -0.47
     passively
    -0.47
    (!__
    -0.47
     Guille
    -0.47
    POSITIVE LOGITS
     length
    0.89
    length
    0.89
     Length
    0.88
    Length
    0.84
    ength
    0.84
    LENGTH
    0.83
     lenght
    0.72
     Longueur
    0.69
     LENGTH
    0.69
     Länge
    0.68
    Activations Density 0.113%

    No Known Activations