Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 5621
    Prev
    Next
    INDEX
    Explanations

    code snippets related to GUI component definitions and configurations in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ICollection
    -0.50
     Tamil
    -0.50
     сан
    -0.50
     Coimbatore
    -0.49
    batore
    -0.49
    Tamil
    -0.48
    ngrx
    -0.47
     Cauchy
    -0.47
     Madura
    -0.47
    Referencie
    -0.46
    POSITIVE LOGITS
     Q
    1.03
     Qt
    0.88
    Q
    0.86
    QMetaType
    0.84
     QString
    0.74
    QString
    0.74
     qt
    0.74
    QObject
    0.73
    Qt
    0.73
     q
    0.72
    Activations Density 0.110%

    No Known Activations