© 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. 38-GEMMASCOPE-RES-16K
    11. 11366
    Prev
    Next
    INDEX
    Explanations

    specific numerical values, references, and terms related to legal or procedural contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.70
     ſind
    -0.62
    Демографія
    -0.58
    ConstraintMaker
    -0.56
     zoude
    -0.56
     queſta
    -0.56
     مشين
    -0.53
    WriteTagHelper
    -0.50
    Ārējās
    -0.50
    \{\\
    -0.49
    POSITIVE LOGITS
     lainnya
    0.56
     itself
    0.50
     also
    0.50
     Caval
    0.48
     elsewhere
    0.48
     rest
    0.48
     fathom
    0.46
     вообще
    0.45
     alone
    0.45
    的话
    0.45
    Activations Density 1.556%

    No Known Activations