Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 33-GEMMASCOPE-RES-131K
    6. 65951
    Prev
    Next
    INDEX
    Explanations

    geographical locations and routes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_131k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ɵɵelement
    -0.35
    Välislingid
    -0.30
     industriel
    -0.28
     législ
    -0.28
     tas
    -0.28
    TypedDataSet
    -0.27
    zü
    -0.27
     plomb
    -0.26
    gnings
    -0.25
    日语
    -0.25
    POSITIVE LOGITS
     Coachella
    0.94
     Palm
    0.94
    Palm
    0.88
    palm
    0.83
     palm
    0.80
     palms
    0.73
     Palms
    0.70
    achella
    0.70
    PreferredItem
    0.60
     palme
    0.60
    Activations Density 0.019%

    No Known Activations