© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 951
    Prev
    Next
    INDEX
    Explanations

    references to users and user-related attributes in a dataset or code context

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

    references to user-related data or user identifiers across different programming languages and contexts.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     McNally
    -0.44
     McIntosh
    -0.43
    arrête
    -0.42
     McCall
    -0.40
     indah
    -0.39
     keter
    -0.39
    fiehlt
    -0.39
    สำคัญ
    -0.39
    Absch
    -0.39
    <h1>
    -0.39
    POSITIVE LOGITS
     User
    1.16
     user
    1.10
     USER
    1.09
    user
    1.05
     getUser
    1.03
    getUser
    1.00
     Users
    0.98
    USER
    0.98
     setUser
    0.94
     UserController
    0.94
    Activations Density 0.047%

    No Known Activations