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. 13-GEMMASCOPE-RES-16K
    6. 7276
    Prev
    Next
    INDEX
    Explanations

    significant moments or instances in time

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Normdatei
    -0.75
    ddha
    -0.72
     contratto
    -0.71
     Winaray
    -0.69
    uolo
    -0.69
     paroisse
    -0.68
    Autoritní
    -0.67
    rapeau
    -0.67
     besky
    -0.66
     noastre
    -0.66
    POSITIVE LOGITS
     moments
    1.73
    Moment
    1.71
    Moments
    1.67
     moment
    1.65
     Moments
    1.61
     Moment
    1.59
    moments
    1.56
    moment
    1.56
     MOMENT
    1.45
     momento
    1.16
    Activations Density 0.078%

    No Known Activations