© 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. 24-GEMMASCOPE-RES-16K
    11. 782
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts related to physical theories, particularly in quantum mechanics

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

    followed by "from" or related to disappearing

    np_acts-logits-general · gemini-2.0-flash

    apart from

    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
    +#+
    -0.76
    #+#
    -0.59
    TypedDataSet
    -0.59
     XNUMX
    -0.58
    //
    -0.58
    =“
    -0.57
    NUMX
    -0.56
    :+:
    -0.55
     autobio
    -0.52
     #"
    -0.50
    POSITIVE LOGITS
     corresponding
    0.49
     except
    0.48
     quelcon
    0.48
     ganancia
    0.48
     COMPUT
    0.46
     composants
    0.45
     geomé
    0.45
     procédures
    0.44
     only
    0.44
     avantages
    0.44
    Activations Density 3.175%

    No Known Activations