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-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 2514
    Prev
    Next
    INDEX
    Explanations

    references to scientific publications and their citation format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 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
    omenclature
    -0.50
     gelin
    -0.50
    +#+#
    -0.47
     initComponents
    -0.46
    swick
    -0.46
    
    -0.45
     jadx
    -0.45
    ayuno
    -0.45
     summarised
    -0.45
    SerializedSize
    -0.44
    POSITIVE LOGITS
    MigrationBuilder
    0.56
    parsedMessage
    0.45
    InjectAttribute
    0.41
    QMetaType
    0.37
    Хро
    0.36
    TAK
    0.33
    âh
    0.33
    ьаж
    0.33
    บู
    0.32
    func
    0.32
    Activations Density 0.130%

    No Known Activations