© 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. 10-GEMMASCOPE-RES-16K
    11. 3372
    Prev
    Next
    INDEX
    Explanations

    elements and properties related to data structures and JSON-like formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    },[])
    -0.52
     mouth
    -0.46
    flink
    -0.46
    ösungen
    -0.45
     saurait
    -0.45
    "]').
    -0.44
    bals
    -0.43
     réaliste
    -0.42
    bua
    -0.42
     porté
    -0.42
    POSITIVE LOGITS
    клопе
    0.71
     мәкал
    0.71
    IsContent
    0.70
    ⓧ
    0.70
    AccessorTable
    0.66
     تضيفلها
    0.65
    devamını
    0.64
    rungsseite
    0.63
     חיצוניים
    0.59
    elemField
    0.59
    Activations Density 0.732%

    No Known Activations