© 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. 11146
    Prev
    Next
    INDEX
    Explanations

    references to press conferences and related events

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

    press conferences and official public statements by political figures.

    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
    StructEnd
    -0.73
     nahilalakip
    -0.62
    adaptiveStyles
    -0.62
     resourceCulture
    -0.59
     فريبيس
    -0.57
    SharedCtor
    -0.56
    RegistryLite
    -0.54
    évaluateur
    -0.54
     autorytatywna
    -0.51
     noDo
    -0.51
    POSITIVE LOGITS
     press
    1.78
     Press
    1.45
    Press
    1.38
    press
    1.38
     PRESS
    1.35
     Presse
    1.28
     reporters
    1.27
     presse
    1.22
    記者
    1.16
     prensa
    1.14
    Activations Density 0.117%

    No Known Activations