© 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-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 1318
    Prev
    Next
    INDEX
    Explanations

    numerical data and times related to events

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

    Numbers followed by units of time

    np_acts-logits-general · gemini-2.0-flash

    years, days, or times remaining

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
    FormTagHelper
    -0.32
    ++);
    -0.31
     Nö
    -0.31
    ++];
    -0.29
     المعيارى
    -0.28
    tal
    -0.28
     ter
    -0.27
    رها
    -0.27
    足
    -0.26
    食い
    -0.25
    POSITIVE LOGITS
    WireFormatLite
    0.69
     remaining
    0.68
    remaining
    0.66
     MainAxisSize
    0.66
     Remaining
    0.66
    featureID
    0.65
    Remaining
    0.64
     يتيمه
    0.64
    CppMethod
    0.63
     <<<<<<<<<<<<<<
    0.63
    Activations Density 0.216%

    No Known Activations