© 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. 1173
    Prev
    Next
    INDEX
    Explanations

    references to receiving or obtaining something, particularly in contexts related to feedback, data, and support

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

    numerical and financial terms related to transactions, grants, and monetary values.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered 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
    舺
    -0.41
     existing
    -0.40
     we
    -0.40
    writeTo
    -0.40
    TypeDef
    -0.40
     Abel
    -0.39
     Patrimonio
    -0.39
     policiais
    -0.39
    Predecesor
    -0.39
     ouvrage
    -0.38
    POSITIVE LOGITS
     receive
    0.77
     receives
    0.67
     Receive
    0.67
     recib
    0.65
     received
    0.65
     الحره
    0.63
     krijgen
    0.63
     recieve
    0.63
    receive
    0.62
     bekommen
    0.62
    Activations Density 0.264%

    No Known Activations