© 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. 5360
    Prev
    Next
    INDEX
    Explanations

    elements related to guidance and support systems

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

    describing qualities/capabilities

    np_acts-logits-general · gemini-2.0-flash

    concepts and qualities

    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
    хьтан
    -0.61
    RegressionTest
    -0.57
    ⓧ
    -0.53
     GoogleFonts
    -0.50
    TypedDataSet
    -0.50
     financeira
    -0.48
    ﹧
    -0.48
    (;;)
    -0.48
    RTLU
    -0.47
    戬
    -0.46
    POSITIVE LOGITS
    KommentareTeilen
    0.50
    TargetException
    0.34
    rovnik
    0.33
     måte
    0.33
     كن
    0.33
    bleven
    0.31
     fellows
    0.31
    Applause
    0.31
     sowie
    0.30
    ungsbedingungen
    0.30
    Activations Density 0.745%

    No Known Activations