© 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. 5586
    Prev
    Next
    INDEX
    Explanations

    references to dimensions and spatial characteristics in various contexts

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

    "dimension"

    np_acts-logits-general · gemini-2.0-flash

    spatial dimension

    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
    ️
    -0.45
    牌
    -0.44
    UserScript
    -0.42
    Rookie
    -0.39
     Rookie
    -0.39
    a
    -0.38
    -
    -0.37
    er
    -0.37
    A
    -0.36
    Laurie
    -0.36
    POSITIVE LOGITS
    setVerticalGroup
    0.66
     dimension
    0.63
     BoxFit
    0.62
     Dimension
    0.61
    đầm
    0.60
    Dimension
    0.60
    OGND
    0.60
    StoryboardSegue
    0.59
    pendicular
    0.59
     coordinates
    0.58
    Activations Density 0.528%

    No Known Activations