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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 9433
    Prev
    Next
    INDEX
    Explanations

    references to URL redirection and associated concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/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.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -0.61
     مشين
    -0.55
     pungkas
    -0.53
     puentes
    -0.53
     jurídico
    -0.50
     aislada
    -0.50
     laaj
    -0.49
     }{@
    -0.49
     zorgt
    -0.49
     égard
    -0.48
    POSITIVE LOGITS
     vanilla
    0.63
     feder
    0.58
     Federal
    0.57
     ſind
    0.56
     Vanilla
    0.56
     federal
    0.56
     trim
    0.54
     beard
    0.54
     redirection
    0.54
     redirect
    0.54
    Activations Density 0.237%

    No Known Activations