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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 15036
    Prev
    Next
    INDEX
    Explanations

    negations and expressions of limitation or exclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſtill
    -0.60
    antaranya
    -0.60
     ejus
    -0.60
     vocale
    -0.60
     itſelf
    -0.58
     ſhe
    -0.58
     tâche
    -0.57
     onely
    -0.55
     cité
    -0.54
     quæ
    -0.53
    POSITIVE LOGITS
     nor
    0.72
     CURIAM
    0.67
     Nor
    0.64
    neither
    0.62
     Wikimedijinoj
    0.61
    ConstraintMaker
    0.61
     tampoco
    0.61
    GraphicsUnit
    0.60
    ρυ
    0.60
    Nor
    0.59
    Activations Density 0.221%

    No Known Activations