© 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. 10182
    Prev
    Next
    INDEX
    Explanations

    concepts related to complexity and diversity in systems

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

    language related to responsibility, capability, or functions that something provides or enables.

    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
    MRP
    -0.43
    żu
    -0.42
     Biôgrafia
    -0.40
    XXL
    -0.39
     bocca
    -0.39
     discontinuities
    -0.39
     BoxFit
    -0.39
    Zeneca
    -0.39
     IFTT
    -0.39
    mbr
    -0.38
    POSITIVE LOGITS
    ंदीखरीदारी
    0.68
    Życiorys
    0.56
    +:+
    0.56
     الرياضيه
    0.56
    ########.
    0.51
    #
    0.47
    endphp
    0.46
    #+#
    0.46
    
    
    0.45
    帖最后由
    0.44
    Activations Density 0.220%

    No Known Activations