© 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. 19-GEMMASCOPE-RES-16K
    6. 496
    Prev
    Next
    INDEX
    Explanations

    references to various types of warnings and alerts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     even
    -0.87
     anyway
    -0.85
     indeed
    -0.84
     either
    -0.81
     actually
    -0.80
     даже
    -0.76
     justru
    -0.76
    even
    -0.75
     persino
    -0.75
     zwar
    -0.74
    POSITIVE LOGITS
    ItemLayout
    0.68
     וגם
    0.67
     impressive
    0.65
    ))));
    0.58
     affected
    0.56
     betroffen
    0.56
     Италијани
    0.56
     Impressive
    0.53
    ."));
    0.52
    ']).
    0.52
    Activations Density 0.364%

    No Known Activations