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. 11431
    Prev
    Next
    INDEX
    Explanations

    references to financial and investment-related activities or situations

    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
     bande
    -0.36
     pizz
    -0.35
     Patches
    -0.35
     Artifact
    -0.34
     ch
    -0.34
     Kenne
    -0.33
     plak
    -0.33
    providedIn
    -0.33
     work
    -0.32
     folks
    -0.32
    POSITIVE LOGITS
    ंदीखरीदारी
    0.68
     disambiguazione
    0.66
    脚注の使い方
    0.66
     snippetHide
    0.54
     Backman
    0.52
     envisage
    0.51
    abestanden
    0.50
     ویکی‌پدی
    0.49
    ябре
    0.49
     Hutchison
    0.49
    Activations Density 0.118%

    No Known Activations