Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1764
    Prev
    Next
    INDEX
    Explanations

    complex mathematical expressions and formulas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ainen
    -0.42
    /.
    -0.42
    </blockquote>
    -0.42
    書房
    -0.40
    udar
    -0.40
    strokeWidth
    -0.40
    )`
    -0.40
    httphttps
    -0.39
    ↵↵
    -0.39
    ecma
    -0.39
    POSITIVE LOGITS
     المعيارى
    1.08
    DockStyle
    0.94
     Monfieur
    0.88
    principalTable
    0.83
     gynhyrchwyd
    0.77
    AnchorStyles
    0.75
     preſent
    0.75
     InputDecoration
    0.74
    Personendaten
    0.73
     ExecuteAsync
    0.72
    Activations Density 0.663%

    No Known Activations