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. 8832
    Prev
    Next
    INDEX
    Explanations

    words related to measurement and assessment processes

    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
     autorytatywna
    -1.06
    Hauptartikel
    -1.02
     propOrder
    -0.97
    bootstrapcdn
    -0.96
    protoimpl
    -0.85
    WebElementEntity
    -0.81
    
    -0.81
    ImageContext
    -0.80
    MigrationBuilder
    -0.77
    WriteBarrier
    -0.76
    POSITIVE LOGITS
     серд
    0.54
    ursal
    0.52
     moeilijk
    0.49
    難しい
    0.49
    spesies
    0.48
     Такие
    0.47
     makkelijk
    0.46
     Yet
    0.46
     vanskelig
    0.45
     Theſe
    0.45
    Activations Density 0.202%

    No Known Activations