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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 720
    Prev
    Next
    INDEX
    Explanations

    common prepositions and conjunctions in phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    argout
    -0.64
    migrationBuilder
    -0.62
     ExecuteAsync
    -0.61
     }}"></
    -0.60
    endphp
    -0.60
    UserScript
    -0.59
    lgari
    -0.58
     Ababa
    -0.56
    exprimer
    -0.56
    enderror
    -0.55
    POSITIVE LOGITS
     front
    0.72
    LookAnd
    0.47
     embarrassment
    0.47
     turn
    0.45
    tagHelperRunner
    0.44
    styleable
    0.43
     segreto
    0.43
     ParseException
    0.41
     exchange
    0.41
     troubled
    0.41
    Activations Density 0.228%

    No Known Activations