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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 35542
    Prev
    Next
    INDEX
    Explanations

    programming syntax and function definitions related to hex and decimal conversions

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

    macro definitions with bit shifts

    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
    Datuak
    -0.52
    rungsseite
    -0.49
    flashdata
    -0.48
     DialogResult
    -0.44
    tangentMode
    -0.42
     للمعارف
    -0.42
     GetEnumerator
    -0.42
    wapV
    -0.41
    AndEndTag
    -0.41
    PROLOG
    -0.41
    POSITIVE LOGITS
    StoryboardSegue
    0.41
     TextAppearance
    0.37
    悬
    0.36
     fijne
    0.36
    ConfigureAwait
    0.35
    GEBURTSDATUM
    0.35
     tegens
    0.35
     saites
    0.35
     decade
    0.34
    EndGlobal
    0.34
    Activations Density 0.218%

    No Known Activations