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. 24-GEMMASCOPE-RES-16K
    6. 2428
    Prev
    Next
    INDEX
    Explanations

    code-related definitions and assignments within programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Re" prefix or standalone

    np_acts-logits-general · gemini-2.0-flash

    re, rec, retrans, reticles, release

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LayoutStyle
    -0.59
     виправивши
    -0.56
    ########.
    -0.56
    Autoritní
    -0.56
    rouille
    -0.55
     beginnetje
    -0.54
     بيها
    -0.48
    rat
    -0.46
    BufferException
    -0.45
    piram
    -0.45
    POSITIVE LOGITS
     Re
    2.94
     re
    2.90
    Re
    2.82
     RE
    2.50
    re
    2.38
    RE
    2.19
     ré
    1.98
     Rec
    1.98
     Rew
    1.96
     ре
    1.90
    Activations Density 1.077%

    No Known Activations