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. 1-GEMMASCOPE-RES-16K
    6. 7529
    Prev
    Next
    INDEX
    Explanations

    references to strategic approaches or plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    noc
    -0.46
     constater
    -0.46
     bocca
    -0.45
    currentColor
    -0.45
     bicchiere
    -0.45
     écl
    -0.45
    حياته
    -0.44
    loem
    -0.44
    useum
    -0.44
    viewBox
    -0.44
    POSITIVE LOGITS
     strategy
    4.45
     Strategy
    4.02
    strategy
    4.00
    Strategy
    3.81
     strategies
    3.63
     STRATEGY
    3.59
    strategies
    3.23
     Strategies
    3.19
     estrategia
    3.19
     stratégie
    3.09
    Activations Density 0.057%

    No Known Activations