© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1070
    Prev
    Next
    INDEX
    Explanations

    references to fighting or conflict

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tonode
    -0.87
     kasarigan
    -0.79
    styleType
    -0.78
     Edel
    -0.75
    theless
    -0.73
    ContentAlignment
    -0.72
    arakhand
    -0.70
     ErrIntOverflow
    -0.70
    */].
    -0.70
     conséquence
    -0.69
    POSITIVE LOGITS
     fight
    3.24
    fight
    3.03
     Fight
    2.84
     fights
    2.81
     FIGHT
    2.77
     fighting
    2.72
    Fight
    2.68
     fought
    2.63
    FIGHT
    2.55
     Fighting
    2.55
    Activations Density 0.046%

    No Known Activations