© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 10937
    Prev
    Next
    INDEX
    Explanations

    conditional statements and object type checks in code

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

    Code related to type checking

    np_acts-logits-general · gemini-2.0-flash

    instance checking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    usercontent
    -0.39
    usammen
    -0.36
     fen
    -0.36
    Stor
    -0.36
    </thead>
    -0.33
     reserve
    -0.33
    caria
    -0.33
     ves
    -0.32
    AppCompatTheme
    -0.31
    JsonHelper
    -0.29
    POSITIVE LOGITS
     instanceof
    1.04
     isinstance
    0.90
     isKindOfClass
    0.78
    InstanceOf
    0.77
    isinstance
    0.73
    instance
    0.69
     instance
    0.69
     instancia
    0.68
    getClass
    0.65
    GetType
    0.65
    Activations Density 0.303%

    No Known Activations