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. 3-GEMMASCOPE-RES-16K
    6. 12330
    Prev
    Next
    INDEX
    Explanations

    programming terms and functions related to variable arguments and random number generation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ServiceException
    -0.63
     Jaffe
    -0.57
    voja
    -0.53
    ден
    -0.51
    слов
    -0.51
    TemporalType
    -0.51
    unic
    -0.50
    velser
    -0.50
    enko
    -0.49
     zem
    -0.48
    POSITIVE LOGITS
     nums
    1.68
    kwargs
    1.67
    nums
    1.32
     kwargs
    1.11
    KommentareTeilen
    0.97
    hasNext
    0.94
     Efq
    0.93
     Jefus
    0.90
    +#+#
    0.89
     reaſon
    0.87
    Activations Density 0.024%

    No Known Activations