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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15555
    Prev
    Next
    INDEX
    Explanations

    references to minerals and geological materials

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

    Types of minerals or rocks

    np_acts-logits-general · gemini-2.0-flash

    mineral names and compounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     doInBackground
    -0.59
     onOptions
    -0.52
    GraphicsUnit
    -0.45
    cody
    -0.44
    setminus
    -0.41
    WebElementEntity
    -0.41
    addCriterion
    -0.41
     コード
    -0.40
     bushel
    -0.40
    onActivityResult
    -0.40
    POSITIVE LOGITS
     Quartz
    0.83
     صوتيه
    0.83
     quartz
    0.81
    Quartz
    0.78
    石
    0.75
     виправивши
    0.74
     minerals
    0.73
    quartz
    0.73
     stone
    0.72
    ITE
    0.72
    Activations Density 0.224%

    No Known Activations