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

    Neuronpedia

    APICircuit 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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 28243
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific research methodology and experimental results

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

    specific nanostructures, amines, or scientific findings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     constitucional
    -0.33
     occorre
    -0.31
     stället
    -0.31
     razonable
    -0.29
     destacan
    -0.29
     CURIAM
    -0.29
    อก
    -0.29
     valiente
    -0.28
     règles
    -0.28
     perhatian
    -0.28
    POSITIVE LOGITS
     AssemblyCulture
    0.70
    ValueStyle
    0.68
     незавершена
    0.66
    帖最后由
    0.63
    GEBURTSDATUM
    0.63
    GEBURTS
    0.63
     resourceCulture
    0.61
     CreateTagHelper
    0.59
    ContentAsync
    0.59
    AutoScaleMode
    0.59
    Activations Density 0.083%

    No Known Activations