© 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. 11760
    Prev
    Next
    INDEX
    Explanations

    legal terms and conditions related to rights and responsibilities

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

    formal legal and business language used in disclaimers and official statements.

    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
     مشين
    -0.60
    pushFollow
    -0.59
    labelledby
    -0.53
    SharedDtor
    -0.48
    Биография
    -0.46
    Rüyada
    -0.45
    ValueStyle
    -0.44
     lenker
    -0.44
    참고
    -0.44
    setupUi
    -0.44
    POSITIVE LOGITS
     reserves
    1.75
     reserve
    1.70
     reserved
    1.65
     reserving
    1.51
    reserve
    1.38
    reserved
    1.34
     Reserve
    1.32
     Reserves
    1.31
     reserv
    1.30
     Reserved
    1.29
    Activations Density 0.291%

    No Known Activations