© 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. 5983
    Prev
    Next
    INDEX
    Explanations

    code and programming constructs, particularly related to functions and data structures

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

    code snippets related to programming syntax, particularly variable assignments and function definitions.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered 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
    featureID
    -0.67
     noDo
    -0.62
     contextLoads
    -0.62
     ExecuteAsync
    -0.62
    Tikang
    -0.61
     CanadaChoose
    -0.61
    majánló
    -0.60
    InitVars
    -0.59
     <<<<<<<<<<<<<<
    -0.58
    ]=>
    -0.58
    POSITIVE LOGITS
     naveg
    0.33
     specified
    0.33
    出版年
    0.31
    PRNewswire
    0.29
    JspWriter
    0.28
     propre
    0.28
    Other
    0.28
     approche
    0.28
    jspb
    0.27
    zcze
    0.27
    Activations Density 0.324%

    No Known Activations