© 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. 8-GEMMASCOPE-RES-16K
    11. 10991
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs and thread management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vogli
    -0.47
     EDWIN
    -0.46
     mécan
    -0.45
    からも
    -0.43
    PREFERRED
    -0.43
     lás
    -0.42
    eland
    -0.42
    établissement
    -0.41
     Autó
    -0.41
    chargez
    -0.40
    POSITIVE LOGITS
     HasFactory
    0.90
    GEBURTSDATUM
    0.81
     AttributeSet
    0.81
    IndentedString
    0.81
    /*
    0.77
     SqlParameter
    0.74
    MethodManager
    0.72
    featureID
    0.70
    contentLoaded
    0.69
     дописавши
    0.67
    Activations Density 0.236%

    No Known Activations