Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 377
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computational processes and system management

    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
     itemId
    -0.74
     newItem
    -0.70
     deviceId
    -0.69
     newUser
    -0.68
     pageNo
    -0.62
     statusCode
    -0.61
     Amic
    -0.61
     Nymp
    -0.61
    Portale
    -0.60
     Gai
    -0.57
    POSITIVE LOGITS
    Bind
    0.59
     Descubre
    0.58
    bind
    0.57
    write
    0.56
    show
    0.56
     Seleccione
    0.55
    send
    0.54
     Encuentra
    0.52
    check
    0.52
    build
    0.52
    Activations Density 2.209%

    No Known Activations