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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 15949
    Prev
    Next
    INDEX
    Explanations

    instances of transitions or changes related to data or events

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

    Followed by "<write>" after "<read"

    np_acts-logits-general · gemini-2.0-flash

    read followed by >

    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
    XmlAccessorType
    -0.68
     BoxFit
    -0.66
    ingeki
    -0.60
    pecially
    -0.59
     EClass
    -0.58
    closedir
    -0.57
     alignItems
    -0.57
    solete
    -0.57
    ourite
    -0.57
    ochlor
    -0.56
    POSITIVE LOGITS
     again
    0.83
    again
    0.81
     then
    0.81
     Then
    0.80
     anschließend
    0.76
    Then
    0.76
     puis
    0.75
     다시
    0.75
     finally
    0.72
    然后再
    0.72
    Activations Density 0.513%

    No Known Activations