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. 1-GEMMASCOPE-RES-16K
    6. 13343
    Prev
    Next
    INDEX
    Explanations

    symbols and formatting related to programming and code structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     auroit
    -0.77
     échanges
    -0.77
     refroid
    -0.75
     illustrazione
    -0.73
     sécher
    -0.73
     colgantes
    -0.73
     nicio
    -0.72
     calitate
    -0.72
     aéri
    -0.71
     scienza
    -0.70
    POSITIVE LOGITS
     mono
    0.52
     fos
    0.49
    前
    0.48
     CHORUS
    0.48
     manis
    0.48
     flat
    0.46
     Denis
    0.46
    Mono
    0.45
     ters
    0.45
    mono
    0.44
    Activations Density 0.329%

    No Known Activations