© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 71877
    Prev
    Next
    INDEX
    Explanations

    keywords and terms related to technical implementation and configuration issues

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

    hard coded IDs

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    InitStruct
    -0.40
     sot
    -0.38
     tor
    -0.35
     protoimpl
    -0.35
    StructField
    -0.34
     sca
    -0.34
     Civ
    -0.34
     st
    -0.33
     joaat
    -0.33
    ander
    -0.32
    POSITIVE LOGITS
     snippetHide
    0.67
    ViewFeatures
    0.61
     كومونز
    0.59
     الرياضيه
    0.59
     يتيمه
    0.58
     unnecessarily
    0.57
     propOrder
    0.57
    tvguidetime
    0.55
     needlessly
    0.53
    UnusedPrivate
    0.53
    Activations Density 0.174%

    No Known Activations