© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 31-GEMMASCOPE-RES-16K
    11. 15336
    Prev
    Next
    INDEX
    Explanations

    monetary values and ranges

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

    numerical price ranges or financial values expressed as "between X and Y".

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    usammen
    -0.33
     democracy
    -0.32
    BindView
    -0.32
    czego
    -0.31
     recorded
    -0.30
     viewType
    -0.30
     precis
    -0.30
    uls
    -0.30
     statistically
    -0.30
    =$(
    -0.30
    POSITIVE LOGITS
    новништво
    0.63
    хьтан
    0.60
    Tikang
    0.60
     utafitiHapana
    0.59
    tanleria
    0.57
    :✨
    0.56
    hoeddwyd
    0.56
    around
    0.56
     Савезне
    0.54
    
    0.53
    Activations Density 0.780%

    No Known Activations