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. 24-GEMMASCOPE-RES-16K
    6. 997
    Prev
    Next
    INDEX
    Explanations

    phrases that express negative social attitudes or judgments

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

    Verbs indicating existence or occurrence

    np_acts-logits-general · gemini-2.0-flash

    things that exist or happen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    новништво
    -0.69
    UnusedPrivate
    -0.55
    setVerticalGroup
    -0.53
    reactstrap
    -0.51
     الاطلاع
    -0.50
    fjspx
    -0.49
    DeleteBehavior
    -0.49
    出版年
    -0.49
    verwijspagina
    -0.48
    cloudflare
    -0.47
    POSITIVE LOGITS
     prevalent
    0.62
     practiced
    0.52
     featured
    0.50
     exist
    0.49
     existed
    0.48
     happen
    0.46
     practised
    0.44
     happens
    0.44
     exists
    0.43
     occurred
    0.42
    Activations Density 0.832%

    No Known Activations