© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 15953
    Prev
    Next
    INDEX
    Explanations

    references to specific online services and platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ре
    -0.68
    p
    -0.63
    жется
    -0.62
    ist
    -0.62
    descriptions
    -0.61
    Ре
    -0.61
    mate
    -0.60
     pathlib
    -0.60
    mb
    -0.59
     Cap
    -0.59
    POSITIVE LOGITS
     Yahoo
    2.11
    Yahoo
    1.96
    yahoo
    1.83
     yahoo
    1.78
    HOO
    1.42
     Efq
    1.23
     raiſ
    1.20
     pleaſure
    1.17
     ſta
    1.14
     ſtate
    1.13
    Activations Density 0.014%

    No Known Activations