© 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. 20-GEMMASCOPE-RES-16K
    11. 7759
    Prev
    Next
    INDEX
    Explanations

    programming-related conditional structures and control flow keywords

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

    Mathematical and logical operators

    np_acts-logits-general · gemini-2.0-flash

    code syntax and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     me
    -0.69
    PRNewswire
    -0.65
     tôi
    -0.60
     we
    -0.59
     kami
    -0.58
     us
    -0.57
    ني
    -0.55
     мной
    -0.55
     hình
    -0.54
    Myself
    -0.54
    POSITIVE LOGITS
     getattr
    0.82
    getattr
    0.80
    ]--;
    0.74
     hänen
    0.74
     &(
    0.73
     externi
    0.73
     egli
    0.69
     defaultstate
    0.68
     صوتيه
    0.67
    ArrowToggle
    0.66
    Activations Density 0.179%

    No Known Activations