Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 433
    Prev
    Next
    INDEX
    Explanations

    concepts related to interactions with external influences or environments

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

    Spatial prepositions like "from," "to," "outside," and "within"

    np_acts-logits-general · gemini-2.0-flash

    located outside or within

    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
    #+#
    -0.78
    weds
    -0.53
    AddTagHelper
    -0.53
     الرياضيه
    -0.50
    новништво
    -0.47
    ulkan
    -0.47
    raborty
    -0.45
    istre
    -0.44
    لاثة
    -0.44
    뀜
    -0.43
    POSITIVE LOGITS
     outside
    3.39
     Outside
    3.10
    Outside
    3.03
    outside
    3.03
     OUTSIDE
    2.75
     external
    2.71
     exterior
    2.46
    OUTSIDE
    2.42
     External
    2.36
    external
    2.34
    Activations Density 0.658%

    No Known Activations