© 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. 7-GEMMASCOPE-RES-16K
    11. 15474
    Prev
    Next
    INDEX
    Explanations

    summation expressions in mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     himſelf
    -0.46
     bParam
    -0.45
    ENGLISH
    -0.44
    MigrationBuilder
    -0.43
    Bahasa
    -0.42
     reklama
    -0.42
    kuuta
    -0.42
     kuri
    -0.41
    libft
    -0.41
    theilen
    -0.41
    POSITIVE LOGITS
    ∑
    0.40
    minecraft
    0.40
    protoc
    0.40
    
    0.37
    Xna
    0.37
     MainAxisSize
    0.37
     collectively
    0.36
    wpdb
    0.35
     spalle
    0.35
    mybatisplus
    0.35
    Activations Density 0.671%

    No Known Activations