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. 4763
    Prev
    Next
    INDEX
    Explanations

    words indicating different categories or classifications

    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
    Cartney
    -0.64
     oocytes
    -0.60
    ناع
    -0.55
     Responsibility
    -0.55
     foramen
    -0.54
     Genome
    -0.53
    AttributeName
    -0.52
     resection
    -0.52
     oliva
    -0.52
    FunctionName
    -0.52
    POSITIVE LOGITS
     types
    1.33
     kinds
    1.20
     Types
    1.20
     getType
    1.18
     type
    1.18
     Type
    1.12
     tipos
    1.09
     TYPES
    1.09
     tipo
    1.08
     TYPE
    1.06
    Activations Density 0.347%

    No Known Activations