© 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. 16-GEMMASCOPE-RES-16K
    11. 8641
    Prev
    Next
    INDEX
    Explanations

    phrases indicating physical actions or movements related to getting into or leaving places

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

    Prepositions "in" and "to"

    np_acts-logits-general · gemini-2.0-flash

    prepositions indicating transition

    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
    rfan
    -0.48
     contrast
    -0.46
    ************/
    -0.45
    Fore
    -0.44
    fört
    -0.44
    דיה
    -0.44
    avs
    -0.43
    options
    -0.43
    nock
    -0.43
     Taro
    -0.43
    POSITIVE LOGITS
     estekak
    0.99
    yntaxException
    0.98
    principalColumn
    0.97
     समीक्षाओं
    0.80
     فريبيس
    0.80
     ComVisible
    0.80
    mybatisplus
    0.79
     rid
    0.78
     насељу
    0.78
     initComponents
    0.78
    Activations Density 0.059%

    No Known Activations