© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 58511
    Prev
    Next
    INDEX
    Explanations

    the conjunction "と" indicating connections or relationships

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

    と, さんと, 人と

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     faktisk
    -0.52
     CanadaChoose
    -0.44
     صوتيه
    -0.44
     dàng
    -0.42
     '\\;'
    -0.40
    miljø
    -0.40
     egentlig
    -0.39
    onPause
    -0.39
     للمعارف
    -0.39
     econômica
    -0.38
    POSITIVE LOGITS
    와
    0.81
    と
    0.76
    さと
    0.69
    人と
    0.68
    しと
    0.64
    과
    0.61
     と
    0.59
    與
    0.58
    りと
    0.58
    与
    0.57
    Activations Density 0.009%

    No Known Activations