© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 12502
    Prev
    Next
    INDEX
    Explanations

    legal and regulatory language, particularly regarding contracts and obligations

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

    followed by prepositions or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    contractual obligations and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.59
    ✭✭
    -0.49
     $_"
    -0.46
    にかけて
    -0.44
    pecabe
    -0.44
    helpful
    -0.43
     cieka
    -0.41
    ágenes
    -0.41
    PreferredItem
    -0.41
    useful
    -0.41
    POSITIVE LOGITS
    才能
    1.13
    才行
    1.04
    才可以
    0.81
     inorder
    0.76
    才會
    0.71
    要想
    0.69
     иначе
    0.69
    才有
    0.68
     lest
    0.65
     чтобы
    0.65
    Activations Density 0.491%

    No Known Activations