© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 13690
    Prev
    Next
    INDEX
    Explanations

    words related to openness and possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.71
    migrationBuilder
    -0.63
    el
    -0.57
     =
    -0.55
    e
    -0.54
    டம்
    -0.53
     W
    -0.53
     “
    -0.53
     muối
    -0.52
     PropTypes
    -0.52
    POSITIVE LOGITS
     Anybody
    1.89
     anybody
    1.87
     anyone
    1.86
    anyone
    1.85
    Any
    1.82
     Any
    1.82
     ANY
    1.81
     any
    1.79
     Qualquer
    1.77
     Anyone
    1.76
    Activations Density 0.127%

    No Known Activations