© 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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 13564
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical data and formal documentation

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

    Following "Alle" (German/Dutch "all")

    np_acts-logits-general · gemini-2.0-flash

    Alle musik

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    OGND
    -0.72
    EDEFAULT
    -0.63
    Autoritní
    -0.57
     يتيمه
    -0.55
    +#+#
    -0.54
     pinulongan
    -0.54
    ngua
    -0.54
     людини
    -0.53
    HomeAsUpEnabled
    -0.53
    allowNull
    -0.53
    POSITIVE LOGITS
    SizeF
    0.60
     paren
    0.52
     syste
    0.51
    StackNavigator
    0.49
    STEN
    0.49
     figure
    0.48
    ,‎
    0.48
     prest
    0.48
     signal
    0.46
    taken
    0.46
    Activations Density 0.037%

    No Known Activations