© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12698
    Prev
    Next
    INDEX
    Explanations

    specific symbolic or mathematical elements and expressions

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

    LaTeX mathematical notation, particularly specialized symbols and formatting commands.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    UserScript
    -0.92
    MLLoader
    -0.91
     BoxFit
    -0.79
     للاسماء
    -0.76
     كومونز
    -0.76
    RenderAtEndOf
    -0.75
     ſei
    -0.74
     témoig
    -0.73
    bootstrapcdn
    -0.72
     useAppContext
    -0.71
    POSITIVE LOGITS
     península
    0.44
     guess
    0.35
    :
    0.34
     Antwort
    0.34
    ...
    0.32
     antworten
    0.31
     отве
    0.31
     πάν
    0.30
     middag
    0.30
    তথ্যসূত্র
    0.30
    Activations Density 0.342%

    No Known Activations