© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 14603
    Prev
    Next
    INDEX
    Explanations

    references to user roles and permissions in a computing context

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

    JSON and code syntax elements with specific structural patterns like colons, quotes, curly braces, and property-value pairs.

    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
    पया
    -0.49
     Kalt
    -0.38
    -------------</
    -0.35
    tvrt
    -0.35
    AndEndTag
    -0.35
    ImageContext
    -0.34
    InputTagHelper
    -0.34
    +#+
    -0.33
    akhstan
    -0.33
    enterOuterAlt
    -0.33
    POSITIVE LOGITS
     permissions
    1.23
     permission
    1.21
     Permissions
    1.10
     Permission
    1.10
    Permissions
    1.05
    permission
    1.02
     roles
    1.02
    Permission
    1.02
    permissions
    0.97
     Roles
    0.92
    Activations Density 0.168%

    No Known Activations