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. 8-GEMMASCOPE-RES-16K
    6. 269
    Prev
    Next
    INDEX
    Explanations

    expressions of disagreement or criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.63
    extAlignment
    -0.52
    Datuak
    -0.46
    IndentedString
    -0.45
    SequentialGroup
    -0.45
    Népesség
    -0.45
    Дереккөздер
    -0.42
    ंदीखरीदारी
    -0.42
    IsContent
    -0.42
    centralwidget
    -0.42
    POSITIVE LOGITS
     Italijanski
    0.41
    stück
    0.40
     Que
    0.39
    Lui
    0.38
    CloseOperation
    0.37
     Custom
    0.35
     Cannot
    0.34
     Lui
    0.34
    Rien
    0.33
    IntoConstraints
    0.33
    Activations Density 0.227%

    No Known Activations