© 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. 10-GEMMASCOPE-RES-16K
    11. 1949
    Prev
    Next
    INDEX
    Explanations

    phrases related to planning, suggestion, and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quæ
    -0.54
    XtraReports
    -0.53
     Trench
    -0.50
    παν
    -0.50
    Miri
    -0.49
     atque
    -0.49
     poud
    -0.49
     Muro
    -0.49
     quoque
    -0.48
     púb
    -0.47
    POSITIVE LOGITS
     eben
    0.80
     كومونز
    0.80
    mergeFrom
    0.66
     --
    0.65
     ویکی‌پدی
    0.63
     obviamente
    0.62
     basically
    0.61
    是非常
    0.60
    bhan
    0.60
     المعيارى
    0.59
    Activations Density 0.501%

    No Known Activations