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. 10-GEMMASCOPE-RES-16K
    6. 6109
    Prev
    Next
    INDEX
    Explanations

    concepts related to health and potential medical implications

    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
    verwijspagina
    -0.49
     فريبيس
    -0.48
    Tazama
    -0.46
    عرِّف
    -0.45
    rungsseite
    -0.45
    thâu
    -0.44
     Numerade
    -0.42
     Wicidata
    -0.41
     gyhoeddwyd
    -0.41
     Verbs
    -0.41
    POSITIVE LOGITS
     asupra
    0.46
     considérons
    0.43
     dumne
    0.42
     gehouden
    0.41
     stră
    0.37
    strokeColor
    0.37
    onActivityResult
    0.37
    Protected
    0.36
    didSet
    0.36
     bijzonder
    0.35
    Activations Density 1.405%

    No Known Activations