© 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. 55491
    Prev
    Next
    INDEX
    Explanations

    phrases indicating addition or accumulation

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

    until, to platforms

    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
     userSchema
    -0.56
    もしれません
    -0.54
     ſind
    -0.53
    flam
    -0.53
    Elek
    -0.52
    ugc
    -0.51
     autorytatywna
    -0.50
     мәкалә
    -0.49
    setGeometry
    -0.48
    Agr
    -0.47
    POSITIVE LOGITS
    到
    1.69
     到
    1.32
    到大
    1.01
    到了
    0.94
    到你
    0.86
     đến
    0.79
    至
    0.73
    到的
    0.69
    吃到
    0.68
    跑到
    0.67
    Activations Density 0.003%

    No Known Activations