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. 39-GEMMASCOPE-RES-16K
    6. 1010
    Prev
    Next
    INDEX
    Explanations

    instances of significant financial data or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Whilst
    -0.84
    Whilst
    -0.80
     our
    -0.65
     fucking
    -0.65
     FUCKING
    -0.64
     whilst
    -0.63
    Figure
    -0.60
     Firstly
    -0.60
    fucking
    -0.59
    एँ
    -0.59
    POSITIVE LOGITS
    Officials
    0.68
     Officials
    0.67
     officials
    0.64
    ¦
    0.60
     ¦
    0.57
     Gov
    0.57
    “(
    0.57
     etwa
    0.55
     staffers
    0.54
    MigrationBuilder
    0.54
    Activations Density 0.206%

    No Known Activations