© 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. 6-GEMMASCOPE-RES-16K
    6. 13151
    Prev
    Next
    INDEX
    Explanations

    references or citations in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Meksiku
    -0.97
     Hartman
    -0.89
    findpost
    -0.87
    RunWith
    -0.87
    ={({
    -0.85
    \{\\
    -0.84
     HasFactory
    -0.83
    GraphicsUnit
    -0.82
     عرض
    -0.82
     Sauer
    -0.81
    POSITIVE LOGITS
    ref
    1.63
    Ref
    1.61
     ref
    1.59
     Ref
    1.54
     REF
    1.25
     useRef
    1.05
    REF
    1.04
    refs
    1.02
    Refs
    1.01
     refs
    0.95
    Activations Density 0.202%

    No Known Activations