© 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. 22-GEMMASCOPE-RES-16K
    6. 5772
    Prev
    Next
    INDEX
    Explanations

    comparative phrases and distinctions between various subjects or groups

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

    preceding "ones" or "those"

    np_acts-logits-general · gemini-2.0-flash

    ones and those

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsMutable
    -0.85
     betweenstory
    -0.80
    MigrationBuilder
    -0.69
    RegressionTest
    -0.68
    migrationBuilder
    -0.68
     aceste
    -0.68
    TintMode
    -0.65
     resourceCulture
    -0.65
     fieldNum
    -0.64
    ()}>
    -0.63
    POSITIVE LOGITS
     ones
    3.58
     those
    3.36
    those
    2.96
    Those
    2.93
     Those
    2.89
     ceux
    2.54
     THOSE
    2.42
     quelli
    2.36
     celles
    2.35
     Ones
    2.19
    Activations Density 1.062%

    No Known Activations