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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 8865
    Prev
    Next
    INDEX
    Explanations

    the beginning of sections or new topics in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -0.63
    verifyException
    -0.61
    Pyx
    -0.58
    ThroughAttribute
    -0.58
    MessageOf
    -0.56
    __("
    -0.56
    SourceChecksum
    -0.53
     forState
    -0.51
    nenie
    -0.50
    ิลปะ
    -0.50
    POSITIVE LOGITS
     Initialized
    0.70
     дописавши
    0.56
     Lumpur
    0.56
    
    0.52
    GraphicsUnit
    0.52
     BoxDecoration
    0.49
    entiary
    0.48
    makeConstraints
    0.47
    '))
    0.47
     gula
    0.46
    Activations Density 0.014%

    No Known Activations