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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 8719
    Prev
    Next
    INDEX
    Explanations

    words indicating participation or involvement in various activities or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndInit
    -0.69
    ьаж
    -0.64
    Skocz
    -0.57
    izable
    -0.51
     precedence
    -0.50
    fxml
    -0.50
    oporosis
    -0.49
    uisine
    -0.48
    èque
    -0.48
     उद
    -0.48
    POSITIVE LOGITS
     actively
    0.98
     aktif
    0.82
    actively
    0.81
     directly
    0.74
    directly
    0.73
     wholeheartedly
    0.70
    AnimationsModule
    0.69
     actif
    0.67
     pleinement
    0.67
     directa
    0.65
    Activations Density 0.266%

    No Known Activations