© 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. 10802
    Prev
    Next
    INDEX
    Explanations

    intensifiers or qualifiers that emphasize degree, particularly the word "extremely."

    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
    ()?;
    -0.67
    Practices
    -0.66
     PRACTICES
    -0.63
     Practi
    -0.62
     practices
    -0.62
    initis
    -0.62
     Marti
    -0.61
     Bits
    -0.61
    StoryboardSegue
    -0.61
     pili
    -0.61
    POSITIVE LOGITS
    ormous
    0.90
    tinyos
    0.89
     Extremely
    0.89
    Extremely
    0.89
    extremely
    0.85
    Xna
    0.85
     enormous
    0.82
     extremely
    0.81
    Huge
    0.80
    huge
    0.78
    Activations Density 0.094%

    No Known Activations