© 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. 18-GEMMASCOPE-RES-16K
    11. 6510
    Prev
    Next
    INDEX
    Explanations

    syntax structures that indicate conditional statements or errors in configuration

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

    Code snippets with keywords like "return", "if", and "headers"

    np_acts-logits-general · gemini-2.0-flash

    function return statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    お楽しみに
    -0.59
    Abitanti
    -0.51
    ↵↵
    -0.51
    <eos>
    -0.50
     Kontrolle
    -0.49
    Itoa
    -0.49
    tvguidetime
    -0.49
     roofs
    -0.47
     endforeach
    -0.46
     htmlFor
    -0.45
    POSITIVE LOGITS
    continue
    0.73
     AssemblyProduct
    0.70
    goto
    0.67
    ArrowToggle
    0.66
     يتيمه
    0.65
     préférences
    0.64
    __(/*!
    0.62
     ModelExpression
    0.61
    QMessageBox
    0.61
     Савезне
    0.61
    Activations Density 0.106%

    No Known Activations