© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 27-GEMMASCOPE-RES-16K
    11. 9524
    Prev
    Next
    INDEX
    Explanations

    references to presence or location in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ècie
    -0.30
    endimento
    -0.29
    Werdegang
    -0.28
     lanjut
    -0.27
    üge
    -0.26
     underlie
    -0.26
    WebControls
    -0.26
     коп
    -0.26
     attach
    -0.26
    ीन
    -0.26
    POSITIVE LOGITS
     autorytatywna
    0.63
    InjectAttribute
    0.59
     wireType
    0.56
     Signalez
    0.54
    ISupport
    0.54
    useNewUrlParser
    0.54
    JspWriter
    0.52
    tillery
    0.52
    JsonInclude
    0.52
    SerializedName
    0.52
    Activations Density 0.228%

    No Known Activations