© 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. 15412
    Prev
    Next
    INDEX
    Explanations

    specific nouns and their modifiers in a variety of contexts, particularly in legal or technical language

    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
    EndContext
    -0.59
     ब्रेकडाउन
    -0.57
    醐
    -0.52
     namelijk
    -0.45
    UnusedPrivate
    -0.44
    tagHelperRunner
    -0.44
     Roskov
    -0.44
    ந்த
    -0.43
    neho
    -0.43
    +#+#
    -0.42
    POSITIVE LOGITS
    ных
    0.66
    ная
    0.63
    ные
    0.63
    ную
    0.60
    вые
    0.59
    ными
    0.56
    ских
    0.56
    льных
    0.56
    них
    0.56
    ный
    0.55
    Activations Density 0.337%

    No Known Activations