© 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. 16-GEMMASCOPE-RES-16K
    11. 14608
    Prev
    Next
    INDEX
    Explanations

    references to software updates and new product releases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Introduction of something new

    np_acts-logits-general · gemini-2.0-flash

    announcing new product

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fallu
    -0.66
     démission
    -0.58
     condamné
    -0.57
     dreapta
    -0.56
     avoient
    -0.55
     fondament
    -0.54
     ulei
    -0.54
     dignité
    -0.54
     étoient
    -0.53
     intérieure
    -0.53
    POSITIVE LOGITS
     new
    1.05
     revamped
    0.85
    IUrlHelper
    0.82
    新しく
    0.80
    new
    0.79
    新的
    0.77
    Introducing
    0.77
    新しい
    0.77
     нового
    0.73
     neuen
    0.73
    Activations Density 0.194%

    No Known Activations