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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 114118
    Prev
    Next
    INDEX
    Explanations

    instances of the word "for" and its context in scientific measurements or values

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

    for the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebVitals
    -0.60
    MemoryWarning
    -0.59
    bootstrapcdn
    -0.55
    érience
    -0.53
    waitKey
    -0.52
     '\\;'
    -0.51
    IUrlHelper
    -0.50
    Welfare
    -0.50
    ergies
    -0.50
     filt
    -0.50
    POSITIVE LOGITS
     ویکی‌پدیای
    0.47
    DIPSETTING
    0.45
    rungsseite
    0.43
    GOTREF
    0.40
     diğer
    0.39
    덜
    0.39
     通販
    0.39
     CreateTagHelper
    0.38
    <!--[
    0.37
     actual
    0.36
    Activations Density 0.066%

    No Known Activations