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. 8-GEMMASCOPE-RES-16K
    6. 6077
    Prev
    Next
    INDEX
    Explanations

    descriptions of distances and spatial positioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ธรรม
    -0.42
    的上
    -0.41
     tri
    -0.39
    wie
    -0.38
    itur
    -0.38
     fiduciary
    -0.38
    גרת
    -0.38
     lume
    -0.37
    携
    -0.36
    潜
    -0.36
    POSITIVE LOGITS
    AnchorStyles
    1.13
    IntoConstraints
    1.06
    awtextra
    0.98
     للاسماء
    0.95
    principalTable
    0.89
     distance
    0.89
    ConstraintMaker
    0.88
     afstand
    0.88
     distances
    0.85
    tagHelperRunner
    0.85
    Activations Density 0.338%

    No Known Activations