© 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. 1-GEMMASCOPE-RES-16K
    6. 13128
    Prev
    Next
    INDEX
    Explanations

    technical terms and constructs related to data handling and system processes in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dersfield
    -0.73
    
    -0.68
     متحده
    -0.60
    ImageField
    -0.60
    Hozzáférés
    -0.59
    ṳ
    -0.58
    phosa
    -0.58
    ië
    -0.55
     distance
    -0.55
    ẵn
    -0.54
    POSITIVE LOGITS
    rx
    0.81
    findpost
    0.77
    RX
    0.73
     elk
    0.64
     rx
    0.63
    Rx
    0.62
     RX
    0.61
     Rx
    0.61
    Geplaatst
    0.61
     AspNetCore
    0.61
    Activations Density 2.377%

    No Known Activations