© 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-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 8755
    Prev
    Next
    INDEX
    Explanations

    terms related to conflict and struggle

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "fight"

    np_acts-logits-general · gemini-2.0-flash

    fight for or against

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    英語版
    -0.40
    ########.
    -0.39
    abases
    -0.37
     uș
    -0.35
    @@@@@
    -0.34
    ApiModelProperty
    -0.34
    auces
    -0.34
     Indo
    -0.33
    utriche
    -0.33
     genoemd
    -0.33
    POSITIVE LOGITS
     fought
    1.13
     Fight
    1.00
     fight
    0.95
    fight
    0.94
    Fight
    0.94
    fought
    0.90
     FIGHT
    0.85
    Fighting
    0.85
     against
    0.84
     fighting
    0.81
    Activations Density 0.169%

    No Known Activations