Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 38227
    Prev
    Next
    INDEX
    Explanations

    references to artificial intelligence and related scholarly works

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

    Ai and Chen citations, AICAR

    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
     transfieras
    -0.48
    <<(
    -0.41
     sonst
    -0.37
    LEncoder
    -0.36
    *************/
    -0.36
    不然
    -0.36
    )}-\
    -0.34
     météoro
    -0.34
     astfel
    -0.34
     municipales
    -0.34
    POSITIVE LOGITS
    Ais
    0.65
     Ais
    0.65
     Ai
    0.55
     createState
    0.55
    ########.
    0.51
    Ai
    0.50
     MainAxisSize
    0.49
     Aimee
    0.47
    verwijspagina
    0.47
     ai
    0.46
    Activations Density 0.022%

    No Known Activations