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. 11726
    Prev
    Next
    INDEX
    Explanations

    references to social structures and systems of power

    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
    OGND
    -0.86
     nakalista
    -0.75
     Administrativna
    -0.70
     estekak
    -0.68
     المعيارى
    -0.66
    Diweddarwch
    -0.66
     оригіналу
    -0.65
     BorderSide
    -0.65
     ویکی‌پدی
    -0.63
    ंदीखरीदारी
    -0.60
    POSITIVE LOGITS
     pop
    0.34
    —
    0.34
     diagnostic
    0.33
     san
    0.30
     (
    0.28
     form
    0.28
     POP
    0.28
     Créez
    0.28
     quasi
    0.28
     Examples
    0.27
    Activations Density 0.809%

    No Known Activations