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__L0-22
    6. 13
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_22
    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
     purpoſe
    -0.98
     Monfieur
    -0.94
     fhew
    -0.93
    ."]
    -0.90
     poffible
    -0.90
     ―――――
    -0.87
     myſelf
    -0.87
     becauſe
    -0.86
    ]";
    -0.86
    ()",
    -0.85
    POSITIVE LOGITS
     Williams
    1.23
    boldsymbol
    1.11
    Williams
    1.04
     Smith
    1.02
    mith
    1.00
    y
    0.95
     Kim
    0.94
    s
    0.93
    Kim
    0.92
     williams
    0.90
    Activations Density 0.043%

    No Known Activations