© 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. 6376
    Prev
    Next
    INDEX
    Explanations

    HTML tags and elements

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

    HTML tags or brackets

    np_acts-logits-general · gemini-2.0-flash

    html opening tags

    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
     ujednoznacz
    -0.76
    parsedMessage
    -0.73
    الحياه
    -0.73
    Personendaten
    -0.73
    featureID
    -0.69
    <unused52>
    -0.66
    <unused14>
    -0.66
    [@BOS@]
    -0.66
    <unused68>
    -0.66
     Italijani
    -0.66
    POSITIVE LOGITS
    ><
    0.63
    a
    0.48
    "><
    0.48
     <
    0.46
    <
    0.43
    div
    0.40
    p
    0.38
     trained
    0.38
    img
    0.38
    en
    0.38
    Activations Density 0.152%

    No Known Activations