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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-131K
    6. 68273
    Prev
    Next
    INDEX
    Explanations

    terms related to food production and dietary staples

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

    food diversity and choices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omethyl
    -0.49
    teza
    -0.45
    mnop
    -0.45
     ComVisible
    -0.44
     препратки
    -0.44
    eby
    -0.43
    原始内容存档于
    -0.42
    ScopeManager
    -0.42
     BorderRadius
    -0.42
    randall
    -0.41
    POSITIVE LOGITS
     foods
    0.51
     food
    0.51
    ]=>
    0.49
    foods
    0.46
     cuisines
    0.43
     khẩu
    0.43
    Foods
    0.43
     식
    0.42
     nutritious
    0.41
     jspb
    0.41
    Activations Density 0.039%

    No Known Activations