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-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 7928
    Prev
    Next
    INDEX
    Explanations

    structural elements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ENTI
    -0.57
     V
    -0.57
    ÉN
    -0.54
    UNCH
    -0.54
     pur
    -0.53
    ULT
    -0.53
    Shadow
    -0.52
    IV
    -0.51
     Shadow
    -0.51
    ICZ
    -0.51
    POSITIVE LOGITS
    __':
    
    1.22
    __":
    
    1.12
    ViewFeatures
    1.06
    SharedCtor
    1.03
     дописавши
    0.97
     nakalista
    0.96
    ']")
    0.92
    ViewImports
    0.91
    :]:
    0.90
    uxxxx
    0.90
    Activations Density 0.089%

    No Known Activations