Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 6283
    Prev
    Next
    INDEX
    Explanations

    syntax and structure elements 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 @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MediatR
    -0.62
    AutoresizingMask
    -0.57
    ftagPool
    -0.53
    ąp
    -0.52
     Phry
    -0.51
     الرياضيه
    -0.51
     Pompe
    -0.50
    ngrx
    -0.49
     canina
    -0.49
    Modi
    -0.49
    POSITIVE LOGITS
    ---*/
    0.60
    ungszeit
    0.58
    expandindo
    0.57
    abestanden
    0.56
    MemoryWarning
    0.55
    ISODE
    0.55
     Burch
    0.55
    zugehen
    0.55
     Seasons
    0.53
    Gön
    0.53
    Activations Density 0.035%

    No Known Activations