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

    Neuronpedia

    APICircuit 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. 31-GEMMASCOPE-RES-16K
    6. 15457
    Prev
    Next
    INDEX
    Explanations

    terms related to water and fuel management

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

    "water" or "fuel"

    np_acts-logits-general · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cejas
    -0.29
     tunggal
    -0.29
    ત્
    -0.28
    <h1>
    -0.28
     humanidade
    -0.27
    间
    -0.27
     aquela
    -0.26
    ActivityCompat
    -0.26
    of
    -0.26
    间的
    -0.25
    POSITIVE LOGITS
    RetentionPolicy
    0.79
    bcryptjs
    0.75
     scarcity
    0.74
     consumption
    0.74
     المعيارى
    0.73
     betweenstory
    0.70
     queſta
    0.67
     supply
    0.67
     noDo
    0.66
    wiliwch
    0.65
    Activations Density 0.491%

    No Known Activations