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. 37-GEMMASCOPE-RES-16K
    6. 4552
    Prev
    Next
    INDEX
    Explanations

    elements related to error handling and exception management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     items
    -0.36
    CROSSTALK
    -0.34
     Watch
    -0.34
     bul
    -0.33
     item
    -0.32
    setToolTip
    -0.30
     scra
    -0.30
    addWidget
    -0.30
    setItems
    -0.30
     Shut
    -0.30
    POSITIVE LOGITS
    RenderAtEndOf
    0.77
    printStackTrace
    0.75
    tagHelperRunner
    0.74
    __':
    
    0.69
    hashCode
    0.67
    ")));
    
    0.64
    orianCalendar
    0.63
    __':
    0.62
    发表于
    0.62
    }-*/;
    0.61
    Activations Density 0.119%

    No Known Activations