© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 2958
    Prev
    Next
    INDEX
    Explanations

    references to historical documents and literary works

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

    references to historical records and scholarly works related to literary and cultural studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ProtoMessage
    -0.60
     ujednoznacz
    -0.59
    qPCR
    -0.57
    rungsseite
    -0.55
    <eos>
    -0.51
     https
    -0.50
    الحياه
    -0.49
     ویکی‌پدیای
    -0.49
    ↵↵
    -0.49
    <strong>
    -0.49
    POSITIVE LOGITS
     CWE
    0.71
     Efq
    0.66
     raiſ
    0.64
     iſt
    0.63
    ſelf
    0.61
    oredCriteria
    0.60
     uſ
    0.58
    StoryboardSegue
    0.58
     Jefus
    0.57
    ſelves
    0.57
    Activations Density 0.270%

    No Known Activations