© 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. 28-GEMMASCOPE-RES-16K
    11. 9145
    Prev
    Next
    INDEX
    Explanations

    code-related syntax and structure elements in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code or script-related tokens

    np_acts-logits-general · gemini-2.0-flash

    code and programming artifacts

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Reſ
    -0.54
     müſſen
    -0.52
    cessite
    -0.51
     ſta
    -0.50
    niſſe
    -0.49
    \,.
    -0.48
     ſtand
    -0.48
    ?";
    -0.48
     ſind
    -0.47
    posedge
    -0.47
    POSITIVE LOGITS
     ayrıca
    0.48
     =
    0.43
     |=
    0.40
    Personensuche
    0.40
     inoltre
    0.39
    SuppressLint
    0.39
     onCreateView
    0.39
    
    0.38
    ßerdem
    0.38
    리는
    0.37
    Activations Density 0.329%

    No Known Activations