© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 739
    Prev
    Next
    INDEX
    Explanations

    legal and regulatory language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hasia
    -0.52
    ORAL
    -0.44
    moveToNext
    -0.44
    ご了承ください
    -0.43
     تضيفلها
    -0.41
    orien
    -0.41
     numberWith
    -0.41
    liferay
    -0.39
    uawei
    -0.39
    `)
    -0.39
    POSITIVE LOGITS
     or
    3.36
     или
    2.52
    หรือ
    2.25
     hoặc
    2.23
     atau
    2.20
    或
    2.20
     alebo
    2.09
     یا
    2.09
    或者
    1.98
     eller
    1.97
    Activations Density 11.112%

    No Known Activations