© 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. 21-GEMMASCOPE-RES-16K
    11. 2569
    Prev
    Next
    INDEX
    Explanations

    specific terms related to obstacles and challenges in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -0.62
     PLWABN
    -0.46
     TestCase
    -0.45
    poons
    -0.44
    šče
    -0.44
    announce
    -0.44
    ագրություններ
    -0.43
    orias
    -0.42
    ⎩
    -0.42
     Woh
    -0.42
    POSITIVE LOGITS
     preventing
    1.90
     hindering
    1.81
     hinder
    1.74
     prevent
    1.73
     prevents
    1.73
     blocking
    1.71
    prevent
    1.66
     hindrance
    1.66
     impediment
    1.65
     prevented
    1.64
    Activations Density 0.985%

    No Known Activations