© 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. 20-GEMMASCOPE-RES-16K
    11. 7907
    Prev
    Next
    INDEX
    Explanations

    prepositions and indicators of location or direction within a text

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

    "in order" or "in ... in" phrases

    np_acts-logits-general · gemini-2.0-flash

    in which

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ddelweddau
    -0.68
     mẽ
    -0.62
    jsonwebtoken
    -0.60
    θρώ
    -0.60
    WebElementEntity
    -0.59
    apunov
    -0.58
    ":
    -0.57
     gynhyrchwyd
    -0.57
    ✨:
    -0.56
    )__
    -0.56
    POSITIVE LOGITS
     which
    1.64
    which
    1.38
     WHICH
    1.19
    Which
    1.08
     whom
    1.07
     Which
    1.04
     cui
    1.04
     lequel
    0.98
     cuyo
    0.92
     whose
    0.92
    Activations Density 1.078%

    No Known Activations