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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 4711
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of "bootstrap" in statistical analysis or algorithms

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

    bootstrap sampling and particle filters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.75
    MigrationBuilder
    -0.68
    MessageOf
    -0.51
    ThroughAttribute
    -0.48
    */;
    -0.48
    MessageTagHelper
    -0.48
    MIDDLEWARE
    -0.47
    dataclass
    -0.47
    IUrlHelper
    -0.47
    ynb
    -0.47
    POSITIVE LOGITS
    Bootstrap
    2.23
    bootstrap
    2.05
     bootstrap
    1.98
     Bootstrap
    1.64
     bootstra
    1.49
     BOOT
    1.08
    BOOT
    1.08
     boot
    1.04
    boot
    1.03
    Boot
    1.00
    Activations Density 0.004%

    No Known Activations