© 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. 8314
    Prev
    Next
    INDEX
    Explanations

    references to clinical and scientific terminology

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

    Code, configuration, or technical syntax

    np_acts-logits-general · gemini-2.0-flash

    parenthetical content or phrases

    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
     femeninos
    -0.35
    featureID
    -0.35
    NullException
    -0.33
     chi̍t
    -0.33
    retudo
    -0.33
    berdayakan
    -0.33
     »)
    -0.33
    facts
    -0.33
    )>>
    -0.32
    cipar
    -0.31
    POSITIVE LOGITS
     '\\;'
    0.67
    └──
    0.59
    AndEndTag
    0.57
    EndGlobalSection
    0.57
     autorytatywna
    0.54
     ujednoznacz
    0.54
     propOrder
    0.53
    AutoModerator
    0.51
    TabIndex
    0.51
    GEBURTS
    0.49
    Activations Density 0.222%

    No Known Activations