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

    Neuronpedia

    APICircuit 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. 7163
    Prev
    Next
    INDEX
    Explanations

    instances of equipment and installation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    auxiliary and modal function words that signal passive voice, possibility/necessity, and connective structure in formal or technical prose.

    oai_token-act-pair · gpt-5Triggered by @arielgoldsteinlab
    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
     amounts
    -0.42
     wages
    -0.41
     efforts
    -0.41
     levels
    -0.41
     contato
    -0.40
     veiks
    -0.38
    はじめに
    -0.38
     issues
    -0.38
     warnings
    -0.37
     quotes
    -0.37
    POSITIVE LOGITS
    LookAnd
    0.80
    رشف
    0.65
     nonUne
    0.63
     للمعارف
    0.63
    RenderAtEndOf
    0.60
    yntaxException
    0.60
     contextLoads
    0.59
     виправивши
    0.59
     ddelweddau
    0.59
    WithIOException
    0.56
    Activations Density 0.901%

    No Known Activations