© 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. 25-GEMMASCOPE-RES-16K
    11. 2910
    Prev
    Next
    INDEX
    Explanations

    references to confrontations and physical altercations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     percolation
    -0.54
     isother
    -0.52
    NamedQueries
    -0.50
    ỡi
    -0.49
     drought
    -0.49
     Lindley
    -0.49
    </tfoot>
    -0.49
    torie
    -0.47
    tonode
    -0.47
    TextUtils
    -0.46
    POSITIVE LOGITS
     punches
    1.31
     punching
    1.16
     punched
    1.10
     brawl
    1.06
     fists
    1.05
     punch
    1.04
     assaulting
    1.03
     assault
    1.03
     fights
    1.02
     assaulted
    1.02
    Activations Density 0.495%

    No Known Activations