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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 885
    Prev
    Next
    INDEX
    Explanations

    code-related structures, particularly functions and their attributes in programming

    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
    ixante
    -0.39
    ourtney
    -0.38
    Closure
    -0.38
     estekak
    -0.38
    expandindo
    -0.37
     հղումներ
    -0.37
     Binnen
    -0.37
    Rujuakan
    -0.36
     برانيه
    -0.36
     Leinwand
    -0.35
    POSITIVE LOGITS
     NPC
    0.78
     attack
    0.75
     npc
    0.75
     combat
    0.72
     damage
    0.72
     Attack
    0.71
     Damage
    0.70
     creature
    0.68
     attacker
    0.68
     weapon
    0.68
    Activations Density 0.514%

    No Known Activations