© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 121939
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and related references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     hyö
    -0.49
     esimer
    -0.47
     bendera
    -0.46
     näky
    -0.44
    acamata
    -0.42
     disables
    -0.42
    fär
    -0.42
    parency
    -0.42
     chimiques
    -0.41
    zzleHttp
    -0.41
    POSITIVE LOGITS
    
    0.69
    ⓧ
    0.54
     transfieras
    0.50
    клопе
    0.50
    期刊论文
    0.49
    devamını
    0.46
    __(/*!
    0.46
     life
    0.46
    RTHOOK
    0.45
     career
    0.45
    Activations Density 0.030%

    No Known Activations