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. 75181
    Prev
    Next
    INDEX
    Explanations

    phrases related to time and objects involved in events

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

    time and specific durations

    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
    s
    -0.81
    ième
    -0.47
    stanbul
    -0.47
    ohjel
    -0.47
     onPause
    -0.46
     kérd
    -0.45
    Ведь
    -0.45
    still
    -0.44
    zerű
    -0.44
    sver
    -0.43
    POSITIVE LOGITS
    <bos>
    0.90
    𝓵
    0.74
    𝓲
    0.67
    𝓮
    0.66
    𝓭
    0.65
    𝓴
    0.65
    𝓫
    0.62
    𝓯
    0.61
     Ader
    0.60
    ン
    0.60
    Activations Density 0.034%

    No Known Activations