© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 5945
    Prev
    Next
    INDEX
    Explanations

    references to tables and data presentation formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     javafx
    -0.59
     useEffect
    -0.58
    сылкі
    -0.57
    ఊ
    -0.56
    getItemId
    -0.56
    UseVisualStyle
    -0.54
     Goode
    -0.54
    //}
    -0.53
     useRef
    -0.53
     bonnes
    -0.53
    POSITIVE LOGITS
     Table
    2.79
    Table
    2.70
     TABLE
    2.09
    TABLE
    2.02
     table
    1.96
    table
    1.86
     Tables
    1.63
    Таблица
    1.42
     tables
    1.38
    Tabla
    1.38
    Activations Density 0.151%

    No Known Activations