© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 126384
    Prev
    Next
    INDEX
    Explanations

    terms related to indicators, warnings, and alerts related to safety and security

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

    warning and indication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    AnchorStyles
    -0.54
    WritableDatabase
    -0.50
     المعيارى
    -0.49
     насељу
    -0.43
    getProfile
    -0.42
     wyg
    -0.42
    uronic
    -0.40
    serviceWorker
    -0.40
    linearGradient
    -0.40
    eleste
    -0.40
    POSITIVE LOGITS
     warnings
    0.58
     warning
    0.57
     advertencia
    0.56
     gynhyrchwyd
    0.53
    warnings
    0.50
     warn
    0.48
     Warnings
    0.48
    warning
    0.46
     indication
    0.46
     warns
    0.45
    Activations Density 0.055%

    No Known Activations