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 - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 1188
    Prev
    Next
    INDEX
    Explanations

    code blocks with specific structures or syntax

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

    closing code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    fjspx
    -0.82
     للاسماء
    -0.75
    Autoritní
    -0.73
    uxxxx
    -0.71
    RTLR
    -0.71
    UpInside
    -0.71
     typelib
    -0.71
     contextLoads
    -0.71
    Hozzáférés
    -0.69
    Хьажоргаш
    -0.67
    POSITIVE LOGITS
     sesuai
    0.37
    .
    0.36
     respective
    0.34
    rub
    0.32
    age
    0.30
     согласно
    0.30
     g
    0.28
     according
    0.28
     hopefully
    0.28
    respective
    0.28
    Activations Density 0.004%

    No Known Activations