© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 101608
    Prev
    Next
    INDEX
    Explanations

    mentions of scams and fraudulent activities

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

    Words describing digital security threats, online scams, fraudulent activities, and malicious communications in discussions about internet safety and cybersecurity concerns.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     נוס
    -0.37
     champion
    -0.35
     smoker
    -0.35
     slou
    -0.35
     wounded
    -0.34
     autonomia
    -0.34
     configureStore
    -0.32
     instrumental
    -0.31
     superiore
    -0.31
     reliable
    -0.30
    POSITIVE LOGITS
     estekak
    0.55
    featureID
    0.54
    Identyfik
    0.53
     SwitchCompat
    0.49
     actionMode
    0.47
    ɵɵelementStart
    0.47
    دانشنامهٔ
    0.47
    hyrchwyd
    0.47
    odoo
    0.46
    BufferException
    0.46
    Activations Density 0.007%

    No Known Activations