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
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 12323
    Prev
    Next
    INDEX
    Explanations

    names and statistics related to sports players

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    transQ
    -0.53
     gwaran
    -0.49
     labios
    -0.47
     Réponses
    -0.47
    zoo
    -0.46
     embreagem
    -0.45
     utile
    -0.45
     informing
    -0.45
    ंदीखरीदारी
    -0.44
    국
    -0.44
    POSITIVE LOGITS
    يكب
    0.46
    исленность
    0.38
    contentLoaded
    0.36
     rabb
    0.35
    >(&
    0.35
    $}}
    0.35
    himovic
    0.34
    endsection
    0.34
    webElementGuid
    0.33
     unplayable
    0.32
    Activations Density 0.252%

    No Known Activations