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
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7549
    Prev
    Next
    INDEX
    Explanations

    themes related to personal growth and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.68
    OGND
    -0.61
     autorytatywna
    -0.57
    帖最后由
    -0.55
    原始内容存档
    -0.54
    GIVEREF
    -0.53
     estekak
    -0.52
     tartalomajánló
    -0.51
    +#+#
    -0.51
    Javadoc
    -0.50
    POSITIVE LOGITS
     ajuns
    0.52
    に至
    0.43
     came
    0.42
    経緯
    0.42
     Entstehung
    0.42
     ontstaan
    0.41
     geliş
    0.40
     powst
    0.40
     résulte
    0.39
     finalmente
    0.38
    Activations Density 0.412%

    No Known Activations