© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 42904
    Prev
    Next
    INDEX
    Explanations

    repeated references to retention, particularly in contexts related to recognition or data storage criteria

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

    retention bonus, time, or positively

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    afficheront
    -0.44
     يتيمه
    -0.40
     Duarte
    -0.40
     Natur
    -0.40
     hæ
    -0.39
    Cuál
    -0.39
    MODIFY
    -0.39
    aronder
    -0.38
     useful
    -0.38
     Felsen
    -0.38
    POSITIVE LOGITS
    rungsseite
    0.62
    AndEndTag
    0.50
    slidesToShow
    0.48
    ########.
    0.47
    
    0.46
    $_['
    0.45
     RTI
    0.44
    率
    0.44
    ratulations
    0.43
    multer
    0.43
    Activations Density 0.029%

    No Known Activations