© 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. 17-GEMMASCOPE-RES-16K
    6. 11292
    Prev
    Next
    INDEX
    Explanations

    structured data and graphics code, particularly related to lighting and vector manipulation in a 3D environment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    !*\
    -0.73
    tagHelperRunner
    -0.70
    BeginInit
    -0.68
     مشين
    -0.67
    )");
    
    -0.65
    )|^{
    -0.65
    ')")
    -0.63
    ]")]
    -0.62
    GHIJKLM
    -0.62
    CloseOperation
    -0.61
    POSITIVE LOGITS
    เดียว
    0.61
     createSprite
    0.55
    yntaxException
    0.51
    mybatisplus
    0.51
    ersen
    0.49
     _("
    0.49
     TextStyle
    0.49
    RequestParam
    0.48
     InputDecoration
    0.48
    fromLTRB
    0.47
    Activations Density 0.232%

    No Known Activations