© 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. 2-GEMMASCOPE-RES-16K
    11. 5613
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly dots and question marks

    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
    NewUrlParser
    -0.79
    XmlAccessType
    -0.67
    ValueStyle
    -0.60
    ConstraintMaker
    -0.59
    Хьажоргаш
    -0.58
    mappedBy
    -0.55
    SharedDtor
    -0.54
    strcmp
    -0.53
    Erstellt
    -0.52
     Normdatei
    -0.52
    POSITIVE LOGITS
    :.
    1.69
    -.
    1.66
    /.
    1.66
    ;.
    1.58
     -.
    1.54
    ,.
    1.54
    ?.
    1.52
    !.
    1.51
    =.
    1.38
    <.
    1.38
    Activations Density 0.258%

    No Known Activations