© 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. 37698
    Prev
    Next
    INDEX
    Explanations

    references to death or errors within a context of concern or investigation

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

    death and dying

    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
     disponibilités
    -0.61
     nahilalakip
    -0.57
     avoient
    -0.54
    HasAnnotation
    -0.52
    rungsseite
    -0.51
     quæ
    -0.50
     méri
    -0.50
    されていない
    -0.49
     feroit
    -0.49
    MLLoader
    -0.48
    POSITIVE LOGITS
    ViewFeatures
    0.48
    +#+#
    0.42
    غول
    0.37
    SPATH
    0.36
    NameInMap
    0.36
     كما
    0.36
     Rul
    0.36
     springfox
    0.35
    徘
    0.35
    URLException
    0.35
    Activations Density 0.025%

    No Known Activations