© 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. 14691
    Prev
    Next
    INDEX
    Explanations

    phrases related to progress and advancement

    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
     HasFactory
    -0.77
     prácti
    -0.74
     peggio
    -0.73
     femininos
    -0.72
     nacionais
    -0.71
    GEBURTSDATUM
    -0.70
     }</
    -0.70
     alemanes
    -0.69
    ︎
    -0.68
     vectoriales
    -0.68
    POSITIVE LOGITS
     moves
    1.86
     MOVE
    1.83
     move
    1.80
     Move
    1.77
     Moves
    1.73
     MOV
    1.70
    move
    1.63
     moving
    1.63
    moves
    1.61
    Move
    1.61
    Activations Density 0.115%

    No Known Activations