© 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. 10-GEMMASCOPE-RES-16K
    6. 1929
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and structures related to group theory and dimensional analysis

    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
     ostavi
    -0.48
    ]<<"
    -0.48
     povezave
    -0.47
    migrationBuilder
    -0.46
    CurrentValue
    -0.46
    WebElementEntity
    -0.45
    usine
    -0.45
     BaseActivity
    -0.44
    تفصیلات
    -0.44
    Tikang
    -0.44
    POSITIVE LOGITS
     jadx
    0.69
    rceil
    0.67
     nmax
    0.60
    ClientSize
    0.60
    DebuggerStep
    0.59
     Efq
    0.59
    ADUATE
    0.58
    initializeApp
    0.58
     CGSize
    0.57
    NgModule
    0.56
    Activations Density 1.604%

    No Known Activations