© 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. 5-GEMMASCOPE-RES-16K
    11. 9603
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to documentation or records

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    djangoproject
    -0.78
    antart
    -0.78
    EObject
    -0.70
    jspx
    -0.69
    войства
    -0.69
    labelText
    -0.67
    edizione
    -0.66
    ènement
    -0.65
    länder
    -0.65
    ModelAttribute
    -0.64
    POSITIVE LOGITS
    Rec
    1.93
     Rec
    1.93
     REC
    1.88
    rec
    1.74
     rec
    1.74
    REC
    1.62
     RECRE
    1.24
     Recre
    1.23
     Recreation
    1.22
    Recu
    1.20
    Activations Density 0.124%

    No Known Activations