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. 21-GEMMASCOPE-RES-16K
    6. 15677
    Prev
    Next
    INDEX
    Explanations

    keywords related to website management and hosting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.54
    endpush
    -0.53
    تقاوى
    -0.53
    mybatisplus
    -0.50
     bpy
    -0.50
    IContainer
    -0.44
    findpost
    -0.44
    期刊论文
    -0.43
    featureID
    -0.43
     getAmount
    -0.43
    POSITIVE LOGITS
     website
    1.05
     websites
    0.92
    website
    0.89
     Website
    0.79
     site
    0.78
     hjemmeside
    0.77
     webpage
    0.77
     hemsida
    0.74
     web
    0.74
    websites
    0.72
    Activations Density 0.468%

    No Known Activations