© 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. 22-GEMMASCOPE-RES-16K
    6. 10156
    Prev
    Next
    INDEX
    Explanations

    assertive statements or opinions expressed by the speaker

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

    Sentences starting with "We" or "I" followed by verbs of opinion

    np_acts-logits-general · gemini-2.0-flash

    I/We state opinions and findings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OrBuilder
    -0.66
     Eks
    -0.66
    ыгана
    -0.66
    rsiniz
    -0.64
    存于互联网档案馆
    -0.62
     iſt
    -0.61
     وتسجيلات
    -0.60
     protoimpl
    -0.59
     فريبيس
    -0.59
    PyExc
    -0.58
    POSITIVE LOGITS
     shall
    0.61
     repeat
    0.51
    nutie
    0.50
    sidemargin
    0.47
    舉
    0.47
     vermeld
    0.47
    nościo
    0.46
    struzione
    0.46
    навли
    0.46
    ruimte
    0.45
    Activations Density 0.218%

    No Known Activations