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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 120382
    Prev
    Next
    INDEX
    Explanations

    terms related to electrical conductivity and semiconductor properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    labus
    -0.60
    StoryboardSegue
    -0.58
    endforeach
    -0.53
     محفوظة
    -0.51
    ParseTree
    -0.51
     getRule
    -0.50
    fchen
    -0.50
    MemoryWarning
    -0.50
     engraçadas
    -0.50
    VYMaps
    -0.50
    POSITIVE LOGITS
     conductivity
    0.68
     Conductivity
    0.55
    conductivity
    0.54
    windowFixed
    0.45
     conductive
    0.37
    balleur
    0.36
     piłkarz
    0.35
    LocationManager
    0.35
     traffic
    0.34
     conductance
    0.34
    Activations Density 0.081%

    No Known Activations