© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14325
    Prev
    Next
    INDEX
    Explanations

    HTML and JavaScript code elements related to navigation bars

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

    Code, usernames, and foreign words

    np_acts-logits-general · gemini-2.0-flash

    fixed height

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     Administrativna
    -0.64
    RTLD
    -0.61
     $_"
    -0.58
     $_(
    -0.57
    SharedCtor
    -0.55
     <>",
    -0.55
     Obrador
    -0.51
    хьтан
    -0.50
    หวัด
    -0.50
    NamedQueries
    -0.48
    POSITIVE LOGITS
     initComponents
    0.39
    SupportActionBar
    0.36
    
    0.36
    radura
    0.33
     kişilik
    0.32
     pengaturan
    0.31
    appBar
    0.31
     Extra
    0.30
    rsiniz
    0.30
     funcionar
    0.29
    Activations Density 0.051%

    No Known Activations