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. 1007
    Prev
    Next
    INDEX
    Explanations

    numerical data related to views and votes on content

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

    Numbers followed by parentheses

    np_acts-logits-general · gemini-2.0-flash

    numbers in parentheses

    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
     ब्रेकडाउन
    -0.83
     AssemblyCulture
    -0.79
     ModelExpression
    -0.74
    الحياه
    -0.74
    
    -0.71
    Bibliograf
    -0.70
     gynhyrchwyd
    -0.70
     صوتيه
    -0.69
    Personendaten
    -0.69
     nahilalakip
    -0.68
    POSITIVE LOGITS
     viewers
    0.39
     τά
    0.33
     popularity
    0.33
     audiencia
    0.32
     audience
    0.32
    ExecuteReader
    0.31
     visitors
    0.31
    ísimas
    0.30
     views
    0.30
    +
    0.30
    Activations Density 0.105%

    No Known Activations