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. 4-GEMMASCOPE-RES-16K
    6. 555
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to analytical methods and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.93
    routeProvider
    -0.78
     jspb
    -0.74
    msgSender
    -0.73
    djangoproject
    -0.72
     AssemblyVersion
    -0.72
    NameInMap
    -0.71
     resourceCulture
    -0.68
     виправивши
    -0.67
    CloseOperation
    -0.66
    POSITIVE LOGITS
     analyse
    1.44
     analysis
    1.39
     analyze
    1.37
     analysing
    1.34
     analyzes
    1.32
     Analyse
    1.30
     Analysis
    1.30
     analyses
    1.28
     Analyses
    1.28
     analyzing
    1.28
    Activations Density 1.421%

    No Known Activations