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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 2269
    Prev
    Next
    INDEX
    Explanations

    references to legal or formal proceedings

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

    numbers 1-9 after a digit

    np_acts-logits-general · gemini-2.0-flash

    dates and associated events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
     BoxFit
    -0.51
    MMV
    -0.49
    putInt
    -0.47
    WidgetItem
    -0.47
     break
    -0.45
     FetchType
    -0.44
    באנגלית
    -0.43
    lijst
    -0.43
    audiovisuel
    -0.43
    dataTables
    -0.43
    POSITIVE LOGITS
    ⓧ
    0.67
     препратки
    0.65
    iconque
    0.60
    monix
    0.56
    SourceChecksum
    0.56
     autorytatywna
    0.54
    ueves
    0.54
    
    0.53
     referenties
    0.50
     reafon
    0.50
    Activations Density 0.172%

    No Known Activations