© 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. 28-GEMMASCOPE-RES-16K
    11. 1923
    Prev
    Next
    INDEX
    Explanations

    information related to documentation and coding terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.57
    OGND
    -0.56
    <bos>
    -0.56
    DebuggerNonUser
    -0.55
    دانشنامهٔ
    -0.54
    woon
    -0.53
    writeField
    -0.53
     Geiſt
    -0.53
     Pliny
    -0.53
    痉
    -0.52
    POSITIVE LOGITS
    Ⅱ
    0.43
     disambiguazione
    0.39
     conducción
    0.38
    Ⅲ
    0.38
     vyš
    0.37
    ambilan
    0.36
    Ⅰ
    0.35
     ObjectParameter
    0.35
     existência
    0.35
     existencia
    0.34
    Activations Density 0.021%

    No Known Activations