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-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 2285
    Prev
    Next
    INDEX
    Explanations

    numerical data and measurements

    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
    />";
    -0.71
     dài
    -0.70
     Lightfoot
    -0.70
     vors
    -0.68
    حياته
    -0.68
    subpackage
    -0.66
     AssemblyProduct
    -0.66
     مصرى
    -0.65
    Jody
    -0.65
    Mant
    -0.65
    POSITIVE LOGITS
     nucleation
    0.83
     Zer
    0.80
     nought
    0.77
     hemlock
    0.76
     eczema
    0.76
    Портали
    0.73
    0
    0.72
     skulls
    0.71
     Ersten
    0.70
    marines
    0.70
    Activations Density 1.093%

    No Known Activations