© 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. 40-GEMMASCOPE-RES-16K
    11. 4720
    Prev
    Next
    INDEX
    Explanations

    sequences of alphanumeric characters related to financial currencies or codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.49
     EH
    -0.49
     QS
    -0.46
     LF
    -0.46
     JC
    -0.45
     KD
    -0.44
     WG
    -0.44
     BQ
    -0.44
    YV
    -0.44
     KF
    -0.44
    POSITIVE LOGITS
     ENH
    0.46
     transfieras
    0.43
    itinéraire
    0.42
     VEN
    0.40
    ußt
    0.40
     VEH
    0.39
    новременно
    0.39
     KGB
    0.38
    锈钢
    0.38
     häm
    0.38
    Activations Density 1.362%

    No Known Activations