Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1231
    Prev
    Next
    INDEX
    Explanations

    code-related elements, particularly those associated with programming functions and variables

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

    Azure CLI commands

    np_acts-logits-general · gemini-2.0-flash

    program names and code formatting

    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
    tinyos
    -0.34
     Tienes
    -0.34
    حياتها
    -0.34
     ignored
    -0.32
    @[+][
    -0.30
     Agrega
    -0.30
    AndEndTag
    -0.29
     ब्रेकडाउन
    -0.29
     nakalista
    -0.29
    <?
    -0.29
    POSITIVE LOGITS
    UrlResolution
    0.53
    WriteLiteral
    0.50
    Butler
    0.49
    TCS
    0.49
    MethodManager
    0.48
     TType
    0.46
     Capitals
    0.46
     propOrder
    0.46
    balt
    0.45
     CLP
    0.45
    Activations Density 0.556%

    No Known Activations