© 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. 64252
    Prev
    Next
    INDEX
    Explanations

    phrases related to attempts or efforts in coding and programming

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

    player's turn

    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
    awtextra
    -0.82
    contentLoaded
    -0.81
    IsMutable
    -0.75
     незавершена
    -0.71
    InjectAttribute
    -0.70
     betweenstory
    -0.68
     Signalez
    -0.68
    StoryboardSegue
    -0.66
    SharedCtor
    -0.65
    RTSN
    -0.65
    POSITIVE LOGITS
     really
    0.44
     messed
    0.40
     gonna
    0.40
     fucked
    0.37
     crazy
    0.34
     stuff
    0.34
     paja
    0.34
     tertentu
    0.33
    Sitio
    0.33
     nicely
    0.32
    Activations Density 0.009%

    No Known Activations