© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 13254
    Prev
    Next
    INDEX
    Explanations

    directional words and phrases related to movement

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

    Directional words (up, back, down, out)

    np_acts-logits-general · gemini-2.0-flash

    back then

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleaſure
    -1.04
     للاسماء
    -0.94
     Efq
    -0.94
     fevere
    -0.90
     ſeveral
    -0.87
     Jefus
    -0.85
     Chriftian
    -0.81
     Monfieur
    -0.80
     Houſe
    -0.80
     Diſ
    -0.79
    POSITIVE LOGITS
    Билгалдахарш
    0.61
     виправивши
    0.60
     חיצוניים
    0.59
     round
    0.58
     ya
    0.58
     down
    0.57
     comp
    0.54
     here
    0.53
     out
    0.53
     over
    0.53
    Activations Density 0.127%

    No Known Activations