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. 19-GEMMASCOPE-RES-16K
    6. 2495
    Prev
    Next
    INDEX
    Explanations

    syntactic structures used in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cucharadita
    -0.54
     caccia
    -0.53
     döv
    -0.52
     affatto
    -0.52
     justement
    -0.51
     morire
    -0.51
    This
    -0.50
     soprav
    -0.49
     giusta
    -0.49
    -(
    -0.49
    POSITIVE LOGITS
     etc
    1.07
     Савезне
    1.02
    MigrationBuilder
    0.94
    Autoritní
    0.90
     *,
    0.87
    WireFormatLite
    0.86
    EndContext
    0.85
    '],$
    0.84
    __',
    0.83
     disponibilités
    0.83
    Activations Density 0.219%

    No Known Activations