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. 9-GEMMASCOPE-RES-131K
    6. 107923
    Prev
    Next
    INDEX
    Explanations

    references to different types of user interface elements related to views in programming

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

    UI views and grid views

    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
    parsedMessage
    -0.91
    WriteBarrier
    -0.87
     defaultstate
    -0.84
     שוליים
    -0.81
    EDEFAULT
    -0.77
    httphttps
    -0.76
    Билгалдахарш
    -0.75
    новниш
    -0.75
    flashdata
    -0.74
     EconPapers
    -0.72
    POSITIVE LOGITS
     programação
    0.37
    δη
    0.35
     great
    0.35
     spirit
    0.33
     abordagem
    0.33
     alça
    0.33
     estratégia
    0.32
    gridView
    0.32
     Büyük
    0.32
     perfeita
    0.32
    Activations Density 0.008%

    No Known Activations