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-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 12360
    Prev
    Next
    INDEX
    Explanations

    elements related to recorded conversations and quoted material

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.62
    Datuak
    -0.61
    دانشنامهٔ
    -0.59
     viewDidLoad
    -0.58
     الرياضيه
    -0.58
    AsUp
    -0.54
    )_/¯
    -0.54
    afficheront
    -0.53
    ⓘ
    -0.53
    medies
    -0.53
    POSITIVE LOGITS
     verbatim
    0.85
     excerpts
    0.73
     quotes
    0.71
     dialogue
    0.70
    quotes
    0.67
    InjectAttribute
    0.65
     diálogo
    0.64
     quoted
    0.63
    Quotes
    0.63
    quoted
    0.62
    Activations Density 0.648%

    No Known Activations