Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 55294
    Prev
    Next
    INDEX
    Explanations

    terms related to risk assessment and management in various contexts

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

    potential risks and hazards

    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
     Италијани
    -0.60
    ыгана
    -0.59
     Савезне
    -0.54
     محفوظة
    -0.54
    medriver
    -0.53
    RegressionTest
    -0.52
    Diwedd
    -0.52
    IsContent
    -0.52
     autorytatywna
    -0.51
    xmlWriter
    -0.51
    POSITIVE LOGITS
     COMERC
    0.38
     vulnerabilities
    0.38
     exposure
    0.37
     potential
    0.37
     exposures
    0.37
     threats
    0.36
     identified
    0.35
     SISTEMA
    0.35
     Dasar
    0.35
     Imre
    0.35
    Activations Density 0.018%

    No Known Activations