© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104165
    Prev
    Next
    INDEX
    Explanations

    terms related to victories and defeats in competitive contexts

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

    winning or defeating opponents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aktivitet
    -0.46
    nargs
    -0.40
     ledig
    -0.36
    plaatst
    -0.35
     생
    -0.34
     activity
    -0.34
     arbeid
    -0.33
    GLenum
    -0.33
    成
    -0.32
    isHidden
    -0.32
    POSITIVE LOGITS
     يتيمه
    0.65
    principalTable
    0.59
     ]
    0.58
    ']))
    0.57
    exitRule
    0.57
    '},
    0.55
     objectForKey
    0.54
    enterOuterAlt
    0.53
     }));
    0.52
    Jîn
    0.52
    Activations Density 0.017%

    No Known Activations