© 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. 7536
    Prev
    Next
    INDEX
    Explanations

    references to the term "Mat" and its variations in various contexts

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

    Token "Mat" followed by a letter

    np_acts-logits-general · gemini-2.0-flash

    words starting with mat

    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
    complexType
    -0.65
    oneofs
    -0.64
     autorytatywna
    -0.60
     فريبيس
    -0.60
    Abit
    -0.60
    Clik
    -0.58
    aryen
    -0.57
    FunctionFlags
    -0.54
     CommonModule
    -0.53
     referrerpolicy
    -0.53
    POSITIVE LOGITS
     يتيمه
    0.57
    ArgsConstructor
    0.57
    audiovisuel
    0.52
    ador
    0.51
    providedIn
    0.48
    adors
    0.48
     ожи
    0.48
    inee
    0.47
    urities
    0.47
    resses
    0.47
    Activations Density 0.101%

    No Known Activations