© 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. 4610
    Prev
    Next
    INDEX
    Explanations

    technical and programming-related terms or code structures

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

    database variable names and code identifiers that reference user account data.

    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
     AssemblyProduct
    -0.40
    UrlResolution
    -0.34
    –¿
    -0.32
     Erwä
    -0.31
    cô
    -0.30
    说着
    -0.28
    难
    -0.27
     — 
    -0.26
     Sicilia
    -0.26
     lettera
    -0.26
    POSITIVE LOGITS
     Tapatalk
    0.88
     thread
    0.88
     Thread
    0.87
     Moderator
    0.85
     forum
    0.83
     Mods
    0.81
     moderators
    0.79
     Forum
    0.79
     threads
    0.79
     moderator
    0.78
    Activations Density 0.299%

    No Known Activations