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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3347
    Prev
    Next
    INDEX
    Explanations

    references to scientific theories and individuals related to quantum gravity

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

    physics and cosmology

    np_acts-logits-general · gemini-2.0-flash

    cosmological singularity and instability

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    RTDA
    -0.38
    excluded
    -0.35
    :✨
    -0.35
     фар
    -0.34
    뜬
    -0.33
     bench
    -0.33
     excluded
    -0.32
     الب
    -0.32
     delinquency
    -0.32
    inal
    -0.32
    POSITIVE LOGITS
    schild
    0.52
     OnTriggerEnter
    0.52
    səhifə
    0.52
    Autoritní
    0.51
     jsPsych
    0.49
    لينكات
    0.49
     turística
    0.48
    PreExecute
    0.48
    engkapnya
    0.47
    migrationBuilder
    0.47
    Activations Density 1.157%

    No Known Activations