© 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-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 7420
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting marks in code or string data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    BeginInit
    -0.75
    omla
    -0.62
     Gag
    -0.60
     MainAxisSize
    -0.58
    opre
    -0.57
     Baz
    -0.57
    ifred
    -0.57
    getStringExtra
    -0.56
    setPref
    -0.56
    ($"{
    -0.56
    POSITIVE LOGITS
    migrationBuilder
    0.58
    setupUi
    0.57
     BorderSide
    0.55
     useRef
    0.54
    newtheorem
    0.54
    ngOn
    0.53
    }`).
    0.52
     demas
    0.51
    orghini
    0.51
     старости
    0.50
    Activations Density 0.052%

    No Known Activations