© 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. 6-GEMMASCOPE-RES-16K
    11. 12057
    Prev
    Next
    INDEX
    Explanations

    occurrences of identifiers and creation statements in programming code

    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
    fromnode
    -0.66
    <>("
    -0.63
    thâu
    -0.61
    windowFixed
    -0.58
    /
    -0.58
     Meksiku
    -0.56
     AssemblyVersion
    -0.56
    ="#">
    -0.55
    tonode
    -0.54
     Allociné
    -0.54
    POSITIVE LOGITS
     مشين
    0.77
    IsContent
    0.66
     חיצוניים
    0.65
    ंदीखरीदारी
    0.60
     InputDecoration
    0.59
    STRUCTIONS
    0.59
    存于互联网档案馆
    0.58
     colorWith
    0.57
    abestanden
    0.56
     houſe
    0.56
    Activations Density 0.012%

    No Known Activations