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. 4-GEMMASCOPE-RES-16K
    6. 586
    Prev
    Next
    INDEX
    Explanations

    references to North American entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -0.48
    thâu
    -0.44
     Pública
    -0.41
     V
    -0.41
     needed
    -0.40
    cerv
    -0.40
     diesmal
    -0.39
    tattoo
    -0.39
    telde
    -0.39
     diesel
    -0.39
    POSITIVE LOGITS
    ImageContext
    0.80
    +#+#
    0.77
    ymce
    0.75
    CodeAnalysis
    0.72
     CanadaChoose
    0.72
     Advocate
    0.71
     advocate
    0.70
    原始内容存档于
    0.70
    DockStyle
    0.70
    Advocate
    0.70
    Activations Density 1.470%

    No Known Activations