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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3869
    Prev
    Next
    INDEX
    Explanations

    references to age and teenagers

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

    Ages and age-related terms

    np_acts-logits-general · gemini-2.0-flash

    teenage ages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.62
    <unused23>
    -0.58
    <unused3>
    -0.58
    [@BOS@]
    -0.58
    ロウィン
    -0.58
    쎲
    -0.58
    <unused41>
    -0.58
    <unused52>
    -0.58
    <unused28>
    -0.58
    <unused8>
    -0.58
    POSITIVE LOGITS
     teen
    1.19
     teenage
    1.14
     teens
    1.13
     teenagers
    1.12
     teenager
    1.12
     Teen
    1.09
    Teen
    1.05
     Teens
    0.94
     adolescent
    0.93
     adolescente
    0.89
    Activations Density 0.185%

    No Known Activations