© 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. 24-GEMMASCOPE-RES-16K
    11. 13726
    Prev
    Next
    INDEX
    Explanations

    phrases or concepts related to division and separation

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

    followed by prepositions indicating separation or division

    np_acts-logits-general · gemini-2.0-flash

    split or divided into

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.72
     Efq
    -0.65
     OMITTED
    -0.62
     CreateTagHelper
    -0.60
    omock
    -0.54
    thodon
    -0.53
    INGHAM
    -0.52
    Cordialement
    -0.52
    DataAnnotations
    -0.50
     defStyleAttr
    -0.50
    POSITIVE LOGITS
     apart
    0.90
     asunder
    0.80
     into
    0.70
     evenly
    0.66
    apart
    0.64
     halves
    0.63
    Apart
    0.63
     Apart
    0.63
     equally
    0.61
     ffilmiau
    0.58
    Activations Density 0.280%

    No Known Activations