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. 14695
    Prev
    Next
    INDEX
    Explanations

    the concept of reality in various contexts

    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
     Buon
    -0.74
    <tr>
    -0.72
    ButtonModule
    -0.71
     FZ
    -0.71
    Zug
    -0.69
    omaterial
    -0.68
    }{|
    -0.67
    ers
    -0.67
    FZ
    -0.63
    fz
    -0.63
    POSITIVE LOGITS
    ̓
    0.95
     Chamb
    0.88
     BoxDecoration
    0.85
     Hartmann
    0.84
     cavitation
    0.83
     captivity
    0.83
     Că
    0.80
     OCC
    0.78
     ventricle
    0.78
    ImageContext
    0.78
    Activations Density 0.108%

    No Known Activations