© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 4952
    Prev
    Next
    INDEX
    Explanations

    CSS properties and attributes related to layout and display

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

    CSS property "flex"

    np_acts-logits-general · gemini-2.0-flash

    flex / flexbox

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    帖最后由
    -0.56
     OkHttpClient
    -0.45
    WireFormatLite
    -0.45
    UnknownFieldSet
    -0.45
     surroundings
    -0.44
    Vtbl
    -0.44
     ©️
    -0.41
    SharedDtor
    -0.41
    providedIn
    -0.40
     Coelho
    -0.39
    POSITIVE LOGITS
     flex
    2.67
    flex
    2.58
    Flex
    2.31
     Flex
    2.31
     FLEX
    2.03
    FLEX
    1.99
     flexing
    1.73
     Flexib
    1.33
     flexible
    1.32
     flexion
    1.29
    Activations Density 0.058%

    No Known Activations