© 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. 2785
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their relationships in various contexts

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

    Followed by a relative pronoun or similar

    np_acts-logits-general · gemini-2.0-flash

    person or woman or man

    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
     the
    -0.35
    ,
    -0.33
     multi
    -0.32
     possible
    -0.31
     spring
    -0.31
     full
    -0.31
     Spring
    -0.30
     and
    -0.30
     long
    -0.29
     an
    -0.29
    POSITIVE LOGITS
    parsedMessage
    1.10
    verwijspagina
    1.01
     الرياضيه
    0.90
    المناصب
    0.89
    <unused43>
    0.89
     Dieſe
    0.89
    <unused42>
    0.89
    <pad>
    0.89
    <unused74>
    0.88
    <unused76>
    0.88
    Activations Density 0.893%

    No Known Activations