© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 10607
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and features, particularly islands and plateaus

    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
    PickerController
    -0.55
     transfieras
    -0.53
    heli
    -0.51
    open
    -0.51
    writeFieldEnd
    -0.51
     estimés
    -0.50
    olden
    -0.50
    pted
    -0.49
     thermique
    -0.48
    logues
    -0.48
    POSITIVE LOGITS
     waarop
    0.89
     viewDidLoad
    0.69
    上的
    0.67
    DateTimeField
    0.66
    Bronnen
    0.62
    raded
    0.60
    wapV
    0.58
     surface
    0.58
     للمعارف
    0.57
    ANDUM
    0.56
    Activations Density 0.625%

    No Known Activations