© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 80944
    Prev
    Next
    INDEX
    Explanations

    the presence of single-character or one-letter responses in conversations

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

    I found

    np_acts-logits-general · gemini-2.5-flash-lite

    markers that signal the start of an answer/model response, including the answer delimiter and the first token(s) of the reply.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    DockStyle
    -0.51
     AssemblyCulture
    -0.49
    aarrggbb
    -0.49
    WebpackPlugin
    -0.48
     يتيمه
    -0.47
    SupportActionBar
    -0.46
    رشف
    -0.46
    featureID
    -0.45
    HtmlAttribute
    -0.44
    PreExecute
    -0.44
    POSITIVE LOGITS
    UnsafeEnabled
    0.44
    localctx
    0.34
    ribut
    0.34
    AntiForgeryToken
    0.32
     Guilford
    0.32
    soccer
    0.31
    tvguidetime
    0.31
    prüche
    0.31
     Examiners
    0.31
     Morn
    0.31
    Activations Density 0.002%

    No Known Activations