© 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. 2537
    Prev
    Next
    INDEX
    Explanations

    terms and conditions related to user permissions and administrative practices in computing

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

    words related to administrative privileges and elevated access rights.

    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
     Photocase
    -0.43
    RenderAtEndOf
    -0.42
    Rohy
    -0.40
    yntaxException
    -0.40
     sumpay
    -0.39
    SharedCtor
    -0.39
     autorytatywna
    -0.38
     دیکھیے
    -0.37
     disambiguazione
    -0.36
     ModelExpression
    -0.34
    POSITIVE LOGITS
     admin
    1.67
     administrator
    1.63
     Administrator
    1.52
    admin
    1.52
     Admin
    1.50
    Admin
    1.44
    Administrator
    1.38
     administrators
    1.38
     admins
    1.38
     ADMIN
    1.36
    Activations Density 0.390%

    No Known Activations