© 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. 11-GEMMASCOPE-RES-16K
    6. 4390
    Prev
    Next
    INDEX
    Explanations

    different types of mathematical expressions involving the right parentheses and brackets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     calendriers
    -0.86
     Strickland
    -0.84
     Bundy
    -0.84
    помним
    -0.81
    jména
    -0.80
    Datuak
    -0.76
     Monk
    -0.76
    ENNE
    -0.76
     Kura
    -0.76
    hender
    -0.74
    POSITIVE LOGITS
    right
    1.19
    bigr
    0.92
    >)</
    0.82
    ">)</
    0.75
    I
    0.71
    clerview
    0.70
    ftagPool
    0.69
    RIGHT
    0.67
     Paragu
    0.64
    migrationBuilder
    0.64
    Activations Density 0.159%

    No Known Activations