© 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. 8-GEMMASCOPE-RES-16K
    6. 8965
    Prev
    Next
    INDEX
    Explanations

    data types and function declarations typically found in programming languages, particularly C or C-like syntax

    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
    ]]);
    -0.64
    rimo
    -0.64
     /></
    -0.64
    клопе
    -0.63
    "/></
    -0.62
     Spa
    -0.61
    CrossRef
    -0.61
     grand
    -0.60
    andum
    -0.59
    SPA
    -0.58
    POSITIVE LOGITS
    BYTE
    0.84
     BYTE
    0.82
     Byte
    0.79
    Byte
    0.78
    UCHAR
    0.77
    مراجع
    0.73
    ViewFeatures
    0.73
    byte
    0.72
     byte
    0.70
    UrlResolution
    0.65
    Activations Density 0.153%

    No Known Activations