© 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-2-9B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 15954
    Prev
    Next
    INDEX
    Explanations

    attributes related to width specifications in coding contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     []:
    -0.48
    ](#
    -0.41
    ober
    -0.41
     TEST
    -0.40
    \`
    -0.39
     sessile
    -0.39
     paras
    -0.38
    >//
    -0.38
    SceneManagement
    -0.38
    
    -0.38
    POSITIVE LOGITS
     width
    2.95
    width
    2.92
     Width
    2.63
    Width
    2.61
     widths
    2.23
    WIDTH
    2.20
     WIDTH
    2.09
    宽度
    1.89
    widths
    1.88
     largeur
    1.84
    Activations Density 0.059%

    No Known Activations