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. 46015
    Prev
    Next
    INDEX
    Explanations

    concepts related to the human experience and relational dynamics

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

    even where plaintiff

    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
     and
    -0.37
     instead
    -0.31
    ,
    -0.29
     during
    -0.27
     AssemblyCulture
    -0.27
    LabelTagHelper
    -0.27
     by
    -0.25
     or
    -0.25
     '\\;'
    -0.25
     [
    -0.25
    POSITIVE LOGITS
    ніципалі
    0.83
    +#+#
    0.83
     виправивши
    0.82
     Biôgrafia
    0.77
    :✨
    0.77
    principalColumn
    0.73
    ſelben
    0.72
     vooz
    0.68
     intptr
    0.68
     CallOverrides
    0.66
    Activations Density 0.120%

    No Known Activations