© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 115184
    Prev
    Next
    INDEX
    Explanations

    mentions of users or accounts, likely from social media or collaborative platforms

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

    citations with @

    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
    ChildScrollView
    -0.72
     canst
    -0.62
     '\\;'
    -0.59
     BoxDecoration
    -0.56
     initComponents
    -0.55
    Ivoire
    -0.55
    yeur
    -0.55
    colnshire
    -0.51
    InputBorder
    -0.51
    inobu
    -0.50
    POSITIVE LOGITS
     @
    1.34
    @
    1.30
     "@
    1.05
     '@
    1.02
    .@
    1.00
    ("@
    0.98
    /@
    0.97
    (@
    0.96
    =@
    0.96
    "@
    0.95
    Activations Density 0.210%

    No Known Activations