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. 15032
    Prev
    Next
    INDEX
    Explanations

    punctuation and file path indicators 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
    __':
    
    -0.96
    __':
    -0.78
    __":
    
    -0.70
    tagHelperRunner
    -0.68
     Baillargeon
    -0.66
     actionMode
    -0.63
    География
    -0.62
    RectangleBorder
    -0.62
    principalTable
    -0.62
    ViewFeatures
    -0.61
    POSITIVE LOGITS
    ThroughAttribute
    0.64
    usercontent
    0.59
    SOUNDBITE
    0.53
    ̲
    0.51
    <0xD4>
    0.50
     Paterson
    0.49
     وتسجيلات
    0.48
    HasColumnType
    0.48
    readAs
    0.47
    업
    0.47
    Activations Density 0.016%

    No Known Activations