© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 5742
    Prev
    Next
    INDEX
    Explanations

    commands and references related to web service endpoints and configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Italij
    -0.74
     Hände
    -0.70
     Unterscheidung
    -0.69
     Sünde
    -0.68
     męski
    -0.67
    <bos>
    -0.67
     ilustracja
    -0.66
     oreja
    -0.65
     oscuridad
    -0.65
     Absicht
    -0.65
    POSITIVE LOGITS
     Lo
    0.49
     jScrollPane
    0.45
     Fore
    0.45
     ω
    0.44
     CER
    0.44
     cir
    0.44
     CU
    0.43
     Loc
    0.42
     CM
    0.42
     VAS
    0.42
    Activations Density 1.619%

    No Known Activations