© 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. 24-GEMMASCOPE-RES-16K
    11. 9020
    Prev
    Next
    INDEX
    Explanations

    specific terms and phrases related to technical functions and operations, particularly in engineering or scientific contexts

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

    preceding "to" or "related"

    np_acts-logits-general · gemini-2.0-flash

    not related to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -0.37
     
    -0.30
    なり
    -0.29
    そして
    -0.28
    ä
    -0.27
     can
    -0.27
    2
    -0.27
     ata
    -0.25
    <strong>
    -0.25
    :
    -0.25
    POSITIVE LOGITS
     transfieras
    0.98
     anymore
    0.94
     melainkan
    0.93
     ModelExpression
    0.92
    Personensuche
    0.92
     nor
    0.92
     אלא
    0.92
    Попис
    0.91
    parsedMessage
    0.90
     sondern
    0.90
    Activations Density 1.525%

    No Known Activations