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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 38744
    Prev
    Next
    INDEX
    Explanations

    the beginning of new sections or paragraphs marked by special tokens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.97
    expandindo
    -0.91
     initComponents
    -0.91
     pleaſure
    -0.91
     ujednoznacz
    -0.89
    GEBURTSDATUM
    -0.89
    contentLoaded
    -0.89
     CALIFORNI
    -0.88
     ſever
    -0.82
     whoſe
    -0.82
    POSITIVE LOGITS
     G
    0.56
    umumkan
    0.52
    <bos>
    0.50
     L
    0.49
     őket
    0.47
     muligt
    0.47
     A
    0.47
    Pty
    0.47
    Utils
    0.47
     C
    0.46
    Activations Density 0.000%

    No Known Activations