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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 24398
    Prev
    Next
    INDEX
    Explanations

    monetary transactions and pricing details

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

    retail, ads, Indonesia, Developers, storage, coupons

    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
    MENAFN
    -0.69
    adaptiveStyles
    -0.62
     BorderRadius
    -0.56
    prefixer
    -0.54
    ardless
    -0.53
     SafeMath
    -0.53
     OFDb
    -0.52
     Nier
    -0.52
    zoned
    -0.52
    forums
    -0.52
    POSITIVE LOGITS
     cuerdas
    0.34
    новниш
    0.32
    //
    0.32
     ocupación
    0.30
    цездатний
    0.30
     delegación
    0.29
    Endereço
    0.29
    jaciół
    0.29
     capucha
    0.28
    ņš
    0.28
    Activations Density 0.076%

    No Known Activations