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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 5228
    Prev
    Next
    INDEX
    Explanations

    instances of the word "comment."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    shel
    -0.39
     Success
    -0.37
    Schedulers
    -0.36
    AndFlush
    -0.36
     success
    -0.36
    PreExecute
    -0.36
    DebuggerNonUser
    -0.35
    上
    -0.35
    stood
    -0.35
    =>
    -0.35
    POSITIVE LOGITS
     comment
    1.13
     remark
    0.76
     comments
    0.73
    findpost
    0.72
     complaint
    0.69
     komentar
    0.68
     remarks
    0.68
     complain
    0.66
     komment
    0.64
     Comment
    0.63
    Activations Density 0.269%

    No Known Activations