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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6335
    Prev
    Next
    INDEX
    Explanations

    code structures related to conditional statements and function definitions

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

    Alerts, messages, and notifications

    np_acts-logits-general · gemini-2.0-flash

    display messages or alerts

    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
    DockStyle
    -0.67
    THON
    -0.59
    tvguidetime
    -0.58
    脚注の使い方
    -0.56
    abancı
    -0.55
    setArguments
    -0.55
     Unsc
    -0.55
     ISNI
    -0.53
    Eloquent
    -0.52
    Portale
    -0.52
    POSITIVE LOGITS
     alert
    1.45
    alert
    1.35
     Alert
    1.32
    Alert
    1.25
     message
    1.20
     alerts
    1.17
     warning
    1.12
     notification
    1.09
     Alerts
    1.08
    MessageBox
    1.08
    Activations Density 0.164%

    No Known Activations