© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 6174
    Prev
    Next
    INDEX
    Explanations

    terms related to food science and the analysis of starch modifications

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

    preceding a measurement, element, or condition

    np_acts-logits-general · gemini-2.0-flash

    modified, natural, supplemental, excess, assisted

    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
    Demikian
    -0.54
     препратки
    -0.51
    exitRule
    -0.51
     neatly
    -0.51
     وتسجيلات
    -0.50
    ⎣
    -0.48
     justamente
    -0.47
     picioare
    -0.47
    RTSN
    -0.45
     Савезне
    -0.45
    POSITIVE LOGITS
    EnableWeb
    0.45
     AssemblyVersion
    0.37
    Captor
    0.36
    PyExc
    0.36
     trône
    0.36
    endmodule
    0.34
    saraba
    0.33
     bruk
    0.33
    NewUrlParser
    0.33
    Géographie
    0.32
    Activations Density 1.040%

    No Known Activations