© 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. 9-GEMMASCOPE-RES-131K
    11. 35461
    Prev
    Next
    INDEX
    Explanations

    references to programming language constructs and libraries

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

    pdf testing init

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    astify
    -0.54
     Paglinawan
    -0.52
     onPostExecute
    -0.46
    :✨
    -0.45
    +#+#
    -0.42
     esternos
    -0.42
    engagent
    -0.41
    yych
    -0.41
     PeEnEo
    -0.40
    AnimationsModule
    -0.38
    POSITIVE LOGITS
     Boss
    0.75
    Boss
    0.65
    packageName
    0.64
    Inflater
    0.57
     BOSS
    0.56
    󠁢
    0.52
     packageName
    0.51
     boss
    0.51
    boss
    0.49
    BOSS
    0.48
    Activations Density 0.000%

    No Known Activations