© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 38053
    Prev
    Next
    INDEX
    Explanations

    words indicating prevention and improvement in functionality or performance

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

    functional benefits and improvements

    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
    AutoScaleMode
    -0.48
    bufio
    -0.40
     venn
    -0.30
     помі
    -0.29
    printStackTrace
    -0.29
     internetowa
    -0.28
    ┛
    -0.27
    ୧
    -0.26
     LEAF
    -0.26
    śmy
    -0.26
    POSITIVE LOGITS
     كومونز
    0.65
    MLLoader
    0.60
    <unused55>
    0.58
    <unused57>
    0.58
    <unused58>
    0.57
    <unused10>
    0.57
    <unused40>
    0.57
    <unused42>
    0.57
    <unused15>
    0.57
    <unused7>
    0.57
    Activations Density 0.036%

    No Known Activations