© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 5613
    Prev
    Next
    INDEX
    Explanations

    quantitative data and percentages related to performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intptr
    -0.86
     referrerpolicy
    -0.83
    Personendaten
    -0.74
    Geplaatst
    -0.65
    TypedDataSet
    -0.65
     esboço
    -0.64
    ativement
    -0.64
    GEBURTSDATUM
    -0.62
    numerusform
    -0.60
     newBuilder
    -0.59
    POSITIVE LOGITS
    withstanding
    0.69
     figliu
    0.63
    IUrlHelper
    0.62
     natale
    0.58
     técn
    0.58
     samarbeid
    0.57
     copertura
    0.56
     tempio
    0.56
     âmes
    0.55
    囗
    0.55
    Activations Density 0.500%

    No Known Activations