© 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. 119647
    Prev
    Next
    INDEX
    Explanations

    mentions of financial oversight and insider activities related to corporate governance

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

    personal financial statements

    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
    destination
    -0.39
    感が
    -0.36
    kesmas
    -0.35
     Eunice
    -0.35
     Beal
    -0.34
     Suf
    -0.34
    Destination
    -0.33
    endIndex
    -0.33
    estinos
    -0.33
     mindless
    -0.33
    POSITIVE LOGITS
    Personendaten
    0.63
    MethodManager
    0.62
     esternos
    0.55
    rungsseite
    0.54
    IsPostBack
    0.51
    GEBURTSDATUM
    0.51
    lapsingToolbar
    0.51
    Autoritní
    0.51
    RegistryLite
    0.51
     AssemblyVersion
    0.50
    Activations Density 0.036%

    No Known Activations