© 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. 22-GEMMASCOPE-RES-16K
    11. 16293
    Prev
    Next
    INDEX
    Explanations

    phrases indicating aspirations and expectations for personal achievements

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

    "...the best of our knowledge..."

    np_acts-logits-general · gemini-2.0-flash

    best

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.70
     transfieras
    -0.54
    oredCriteria
    -0.54
    はじめに
    -0.53
    NCIS
    -0.47
    Hvor
    -0.47
     cherchés
    -0.47
    matchCondition
    -0.46
     nonatomic
    -0.45
    힣
    -0.45
    POSITIVE LOGITS
     best
    3.51
    best
    3.23
    Best
    2.94
     Best
    2.86
     BEST
    2.57
    BEST
    2.48
     terbaik
    2.36
     melhor
    2.32
     mejores
    2.31
     mejor
    2.31
    Activations Density 0.273%

    No Known Activations