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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104438
    Prev
    Next
    INDEX
    Explanations

    references to identity and personal interests

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

    Biographical information markers in online profiles, especially personal pronouns, punctuation, and section headers that introduce the author.

    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
    SourceChecksum
    -0.73
    utilisons
    -0.55
    BufferException
    -0.48
     dAtA
    -0.48
    الإنجليزية
    -0.48
    دانشنامهٔ
    -0.47
     برانيه
    -0.46
     calendriers
    -0.46
     <>",
    -0.46
    Erreferentziak
    -0.46
    POSITIVE LOGITS
     enfans
    0.41
    Profile
    0.39
    CommandType
    0.37
     profile
    0.37
     Interests
    0.36
    Вла
    0.36
     ejus
    0.36
    Interests
    0.36
     dandy
    0.36
     Вла
    0.35
    Activations Density 0.032%

    No Known Activations