© 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. 19-GEMMASCOPE-RES-16K
    11. 100
    Prev
    Next
    INDEX
    Explanations

    phrases indicating specificity and attention to details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    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
    -0.76
     beginnetje
    -0.67
     Winaray
    -0.67
    PhysRevLett
    -0.67
    stdc
    -0.67
    RectangleBorder
    -0.66
     BoxFit
    -0.64
     EconPapers
    -0.62
     quæ
    -0.61
    setupUi
    -0.61
    POSITIVE LOGITS
     terhadap
    0.82
     kepada
    0.68
    mybatisplus
    0.61
     into
    0.56
    于
    0.48
    WriteAttribute
    0.47
     about
    0.46
     naar
    0.45
     to
    0.45
     sûr
    0.44
    Activations Density 0.590%

    No Known Activations