© 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. 3-GEMMASCOPE-RES-16K
    11. 6317
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to file management or directory structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    featureID
    -0.67
    setVerticalGroup
    -0.65
    StoryboardSegue
    -0.63
     noDo
    -0.63
    IGraphics
    -0.59
    Seznam
    -0.58
     todella
    -0.57
    تقاوى
    -0.57
     alluminio
    -0.56
    UTELY
    -0.56
    POSITIVE LOGITS
     Hecho
    0.69
     chosen
    0.65
    hado
    0.64
    ée
    0.63
     shown
    0.63
    Shown
    0.61
    Chosen
    0.61
     seen
    0.61
     taken
    0.61
     beaten
    0.60
    Activations Density 0.197%

    No Known Activations