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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3283
    Prev
    Next
    INDEX
    Explanations

    references to plant-feeding larvae and their behaviors

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

    Larvae, caterpillars, and plant feeding

    np_acts-logits-general · gemini-2.0-flash

    caterpillar feeding on plants

    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
    
    -0.61
    setVerticalGroup
    -0.54
    tagHelperRunner
    -0.52
    IntoConstraints
    -0.45
    ">//
    -0.45
    期刊论文
    -0.43
    readystatechange
    -0.43
    Referencer
    -0.42
    LabelTagHelper
    -0.40
    Collegamenti
    -0.39
    POSITIVE LOGITS
     caterpillar
    0.49
    TRIBUN
    0.45
     caterpillars
    0.45
    ivores
    0.42
    ductory
    0.41
    allergenic
    0.41
     eaters
    0.41
    perties
    0.41
     Caterpillar
    0.40
     Seer
    0.40
    Activations Density 0.338%

    No Known Activations