© 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. 9486
    Prev
    Next
    INDEX
    Explanations

    specific sequences and patterns focused on computational or statistical information

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

    after certain symbols or keywords

    np_acts-logits-general · gemini-2.0-flash

    German spy thriller films

    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
     ke
    -0.33
     protégé
    -0.31
     Dorn
    -0.31
     totally
    -0.30
     rut
    -0.30
    )
    -0.30
    uni
    -0.29
     HttpStatusCode
    -0.29
     prote
    -0.29
    from
    -0.29
    POSITIVE LOGITS
     kasarigan
    0.76
     desmotivaciones
    0.70
     Signalez
    0.67
    Hochspringen
    0.66
     $_(
    0.66
     Administrativna
    0.65
     saveiro
    0.65
    SourceChecksum
    0.65
    таратура
    0.65
    Personensuche
    0.63
    Activations Density 4.076%

    No Known Activations