© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 4501
    Prev
    Next
    INDEX
    Explanations

    instances of the particle "を" and the structure of object-focused sentences in the context of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    theless
    -0.65
    出版年
    -0.64
    adays
    -0.61
    selbe
    -0.60
    weil
    -0.60
    course
    -0.59
     שוליים
    -0.59
    行
    -0.59
    __":
    -0.58
     course
    -0.58
    POSITIVE LOGITS
    fjspx
    0.58
    :✨
    0.54
    NameInMap
    0.48
     propOrder
    0.48
    ⓘ
    0.47
    CopyWith
    0.45
     StatefulWidget
    0.44
     PhpStorm
    0.44
    MeasureSpec
    0.43
    Kaynak
    0.42
    Activations Density 0.060%

    No Known Activations