© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 11860
    Prev
    Next
    INDEX
    Explanations

    elements related to programming syntax, particularly in scripting or programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (
    -0.56
    thenReturn
    -0.50
     K
    -0.49
     J
    -0.48
     â
    -0.47
    let
    -0.46
     e
    -0.46
     T
    -0.45
    cal
    -0.45
     to
    -0.44
    POSITIVE LOGITS
     disambiguazione
    0.90
     виправивши
    0.86
     themſelves
    0.85
     myſelf
    0.83
     itſelf
    0.82
     Jefus
    0.79
     raiſ
    0.78
     LoginForm
    0.76
     himſelf
    0.75
     pleaſure
    0.75
    Activations Density 1.959%

    No Known Activations