© 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. 20-GEMMASCOPE-RES-16K
    11. 9316
    Prev
    Next
    INDEX
    Explanations

    terms related to correlation and relationships between variables

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

    words and phrases related to correlation, relationship, and interaction between variables or entities.

    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
     mark
    -0.44
     ControllerBase
    -0.43
    cabul
    -0.42
    inetti
    -0.42
    LayoutInflater
    -0.40
     Mark
    -0.40
    ayar
    -0.39
    Mark
    -0.39
     ileg
    -0.39
     Republik
    -0.39
    POSITIVE LOGITS
     between
    0.71
     miteinander
    0.66
     между
    0.65
     interconnection
    0.60
     intertw
    0.60
     tussen
    0.60
     między
    0.59
     amizade
    0.58
     mellem
    0.56
     між
    0.56
    Activations Density 0.847%

    No Known Activations