© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 98681
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and other symbols often used in coding or mathematical expressions

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

    closing punctuation or delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verwijspagina
    -0.52
    Demografie
    -0.51
    EndGlobalSection
    -0.50
     Italijani
    -0.49
     évêque
    -0.45
    tanleria
    -0.45
     ſever
    -0.44
    IVEREF
    -0.43
     joaat
    -0.41
    adaptiveStyles
    -0.41
    POSITIVE LOGITS
    httphttps
    0.53
    Rhestr
    0.46
    iecie
    0.45
     поси
    0.40
    journal
    0.40
    hospital
    0.40
    hubung
    0.40
     BehaviorSubject
    0.40
    humor
    0.39
    setLength
    0.38
    Activations Density 0.042%

    No Known Activations