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. 1914
    Prev
    Next
    INDEX
    Explanations

    structured programming elements and code-related syntax

    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
    medriver
    -0.46
     Mi
    -0.46
    SizeMode
    -0.45
     Ran
    -0.44
    isio
    -0.43
     A
    -0.43
    かを
    -0.40
    arka
    -0.40
    3
    -0.39
     FAC
    -0.39
    POSITIVE LOGITS
     kasarigan
    1.16
     الرياضيه
    1.02
    aarrggbb
    0.95
    ReusableCell
    0.91
    EndProject
    0.88
    MigrationBuilder
    0.86
    expandindo
    0.86
     المعيارى
    0.83
    Personensuche
    0.83
    contentLoaded
    0.83
    Activations Density 0.381%

    No Known Activations