© 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. 0-GEMMASCOPE-RES-16K
    6. 8569
    Prev
    Next
    INDEX
    Explanations

    repeated occurrences of the word "mad" and references to numerical digits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mtrl
    -0.70
     startY
    -0.58
     /\.(
    -0.57
     StringTokenizer
    -0.56
     fiches
    -0.56
     menor
    -0.56
    extern
    -0.56
    phans
    -0.54
    CRYPT
    -0.54
     tearDown
    -0.53
    POSITIVE LOGITS
     mad
    0.75
    principalColumn
    0.67
    MigrationBuilder
    0.66
    mad
    0.66
    Personendaten
    0.65
     nakalista
    0.64
    thâu
    0.62
     AssemblyCulture
    0.60
     digits
    0.57
    Crazy
    0.57
    Activations Density 0.068%

    No Known Activations