© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 7054
    Prev
    Next
    INDEX
    Explanations

    terms related to health benefits and medicinal properties of substances

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

    Something with "-activity" or "-activities" suffix

    np_acts-logits-general · gemini-2.0-flash

    biological and health effects

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    どれ
    -0.44
    kundige
    -0.42
     lequel
    -0.39
    ramentas
    -0.39
    ODE
    -0.38
    CALLBACK
    -0.37
     sanitarios
    -0.37
     Forest
    -0.37
     interne
    -0.37
     gratuitos
    -0.36
    POSITIVE LOGITS
    AndEndTag
    0.57
     CreateTagHelper
    0.50
    RenderAtEndOf
    0.46
    setVerticalGroup
    0.44
    AISSEE
    0.42
     AssemblyTitle
    0.41
    endphp
    0.41
    AddTagHelper
    0.40
    extAlignment
    0.40
     '\\;'
    0.40
    Activations Density 0.775%

    No Known Activations