© 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. 56557
    Prev
    Next
    INDEX
    Explanations

    references to specific cases and incidents

    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
    Datuak
    -0.76
     يتيمه
    -0.76
    aarrggbb
    -0.73
    amerikanischer
    -0.72
    cknow
    -0.72
     pleaſure
    -0.71
     Diſ
    -0.71
     ujednoznacz
    -0.71
    etheless
    -0.71
     ThemeData
    -0.71
    POSITIVE LOGITS
     fiasco
    0.65
     debacle
    0.61
     thingy
    0.58
     mentioned
    0.57
     thing
    0.56
     alluded
    0.50
     [
    0.49
     we
    0.47
    mentioned
    0.46
     described
    0.46
    Activations Density 0.157%

    No Known Activations