© 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 - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 1836
    Prev
    Next
    INDEX
    Explanations

    technical terms and functions related to coding or programming

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

    authentication credentials and sensitive account information (usernames, passwords, API keys, connection strings).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.50
    prepareStatement
    -0.44
    AndEndTag
    -0.43
    Referencies
    -0.40
    Tembelea
    -0.39
    ErrUnexpectedEOF
    -0.37
     firestore
    -0.36
    蹶
    -0.35
    Collectors
    -0.35
     Hennessy
    -0.35
    POSITIVE LOGITS
     username
    1.58
     Username
    1.38
    username
    1.36
    Username
    1.29
     login
    1.29
     usernames
    1.11
    用户名
    1.10
     Login
    1.10
    USERNAME
    1.10
     credentials
    1.09
    Activations Density 0.205%

    No Known Activations