Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 2509
    Prev
    Next
    INDEX
    Explanations

    conversations about effort, struggle, and interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 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
    Xna
    -0.50
    
    -0.47
    最快更新
    -0.47
    JspWriter
    -0.47
    owie
    -0.45
    licitations
    -0.43
    jgl
    -0.42
    webElementXpaths
    -0.41
     ModelRenderer
    -0.41
     recta
    -0.41
    POSITIVE LOGITS
     but
    0.75
    But
    0.66
     But
    0.65
    but
    0.61
    但
    0.57
    但她
    0.56
     BUT
    0.56
    但这
    0.54
     lakini
    0.54
    但他
    0.54
    Activations Density 0.493%

    No Known Activations