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-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 10159
    Prev
    Next
    INDEX
    Explanations

    technical phrases related to graph theory and circuit concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    modelBuilder
    -0.58
     ActivatedRoute
    -0.48
    endforeach
    -0.48
    igli
    -0.47
     Fifth
    -0.47
     OnEnable
    -0.46
     Dead
    -0.46
    ctober
    -0.46
    3
    -0.45
    mely
    -0.45
    POSITIVE LOGITS
    abestanden
    0.79
     joaat
    0.71
     EconPapers
    0.71
     AssemblyCulture
    0.66
    SuppressLint
    0.66
    DockStyle
    0.65
     OFDb
    0.65
    bootstrapcdn
    0.63
    writeFieldEnd
    0.62
     Мексичка
    0.61
    Activations Density 1.239%

    No Known Activations