© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 12555
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and formulas related to physical systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Position or location in geometric shapes

    np_acts-logits-general · gemini-2.0-flash

    points or centers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.74
     ujednoznacz
    -0.70
     propOrder
    -0.57
    ISupport
    -0.57
    CppCodeGen
    -0.56
     kaarangay
    -0.54
    väg
    -0.53
     createStore
    -0.53
    CodeAttribute
    -0.53
    IVEREF
    -0.51
    POSITIVE LOGITS
     origin
    0.98
     point
    0.89
     midpoint
    0.89
     points
    0.83
     origine
    0.82
     origen
    0.80
     vertex
    0.77
    origin
    0.75
     centre
    0.74
     endpoints
    0.72
    Activations Density 1.111%

    No Known Activations