© 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. 11-GEMMASCOPE-RES-16K
    6. 6552
    Prev
    Next
    INDEX
    Explanations

    characteristics and factors associated with successful educational programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Begriffsklä
    -0.52
     couverture
    -0.51
    <bos>
    -0.51
    prüche
    -0.50
    ẨM
    -0.50
    papier
    -0.49
    EXTERN
    -0.49
    edenken
    -0.48
     Wor
    -0.48
     estrictamente
    -0.48
    POSITIVE LOGITS
     successful
    0.60
    AddTagHelper
    0.57
     ddelweddau
    0.55
    رشف
    0.54
     humaines
    0.54
     @"/
    0.54
    存于互联网档案馆
    0.54
     Successful
    0.54
     pinulongan
    0.53
    successful
    0.52
    Activations Density 0.227%

    No Known Activations