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
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 7109
    Prev
    Next
    INDEX
    Explanations

    references to legal documents or processes related to identification verification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    новниш
    -0.42
    تقاوى
    -0.42
     Wiktionnaire
    -0.39
     naszej
    -0.35
    如果你
    -0.34
    为你
    -0.32
    AppMethodBeat
    -0.32
     znajdziesz
    -0.32
    ]}"
    -0.31
     sämtliche
    -0.31
    POSITIVE LOGITS
    Autoritní
    0.60
     nonUne
    0.58
    routeProvider
    0.54
     betweenstory
    0.49
    httphttps
    0.49
    Previous
    0.47
    tanleria
    0.46
    Tikang
    0.46
    HomeAsUpEnabled
    0.46
     مشين
    0.44
    Activations Density 0.108%

    No Known Activations