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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 14606
    Prev
    Next
    INDEX
    Explanations

    occurrences of the particle "を" used in the context of actions involving feelings

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

    Japanese text followed by を

    np_acts-logits-general · gemini-2.0-flash

    objects of actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    受け
    -0.65
    theless
    -0.63
    行
    -0.61
     Jednak
    -0.59
    selbe
    -0.57
    見
    -0.57
    进了
    -0.56
    見つ
    -0.56
    ously
    -0.56
    ingly
    -0.55
    POSITIVE LOGITS
    fjspx
    0.78
     يتيمه
    0.73
     CreateTagHelper
    0.63
    NameInMap
    0.62
    expandindo
    0.59
    ⓘ
    0.58
     resourceCulture
    0.58
    matchCondition
    0.58
    énario
    0.57
    homonymie
    0.57
    Activations Density 0.064%

    No Known Activations