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. 19-GEMMASCOPE-RES-16K
    6. 3038
    Prev
    Next
    INDEX
    Explanations

    digital time or timestamp elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    众
    -0.52
     acamp
    -0.49
    眾
    -0.45
    sz
    -0.45
     Cole
    -0.45
    ledo
    -0.45
     tích
    -0.45
    Бахар
    -0.44
    Portail
    -0.44
    tagHelper
    -0.43
    POSITIVE LOGITS
    tvguidetime
    0.76
    ConstraintMaker
    0.72
    hematical
    0.68
    InstanceState
    0.67
    ViewInit
    0.64
    rrggbb
    0.64
     ddelweddau
    0.63
     MINUTE
    0.62
     minute
    0.62
     minutes
    0.61
    Activations Density 0.216%

    No Known Activations