Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11662
    Prev
    Next
    INDEX
    Explanations

    references to the name "Taryn" and its variations

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

    starting with "Tar"

    np_acts-logits-general · gemini-2.0-flash

    words starting with Tar followed by specific endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    //
    -0.67
    ément
    -0.64
    Tikang
    -0.63
    culoskeletal
    -0.56
     nakalista
    -0.55
     Leuven
    -0.55
    NameInMap
    -0.54
    worths
    -0.54
    iastes
    -0.53
     noqa
    -0.52
    POSITIVE LOGITS
     Tar
    1.05
    Tar
    1.01
     TAR
    0.92
     tar
    0.91
    tar
    0.88
    TAR
    0.73
     Taran
    0.69
     Taras
    0.66
     Tarragona
    0.66
    DockStyle
    0.65
    Activations Density 0.035%

    No Known Activations