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. 40-GEMMASCOPE-RES-16K
    6. 5777
    Prev
    Next
    INDEX
    Explanations

    dependencies or relationships in programming and logic structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     were
    -0.78
     weren
    -0.74
     هستید
    -0.63
     были
    -0.61
     były
    -0.60
     are
    -0.59
     شدند
    -0.58
    were
    -0.57
     byly
    -0.57
     istnie
    -0.57
    POSITIVE LOGITS
     belongs
    0.68
     lies
    0.65
     fits
    0.63
     liegt
    0.61
     stands
    0.60
     corresponds
    0.60
     suits
    0.59
     stems
    0.59
     ligt
    0.58
     лежит
    0.58
    Activations Density 0.371%

    No Known Activations