© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13128
    Prev
    Next
    INDEX
    Explanations

    relationships between parameters and decisions in a scientific context

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

    infinitive verb constructions, particularly phrases with "to be" and prepositions like "from".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.78
    ValueStyle
    -0.74
    findpost
    -0.74
     للمعارف
    -0.70
    ftagPool
    -0.58
    Билгалдахарш
    -0.58
     تكبرها
    -0.56
    SequentialGroup
    -0.56
    .*")]
    -0.56
     الحره
    -0.56
    POSITIVE LOGITS
     kentang
    0.35
    bildēt
    0.35
     arşivlendi
    0.34
    jahteraan
    0.34
    Бахар
    0.34
    MemoryWarning
    0.33
     ayudado
    0.32
     delantera
    0.32
     plumas
    0.32
    SharedDtor
    0.32
    Activations Density 0.703%

    No Known Activations