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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 15442
    Prev
    Next
    INDEX
    Explanations

    clauses related to historical events and organizational actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.47
    的她
    -0.44
    شان
    -0.41
    ness
    -0.40
    .
    -0.40
     fiecare
    -0.40
    IAm
    -0.39
     além
    -0.38
     fibers
    -0.38
    !
    -0.37
    POSITIVE LOGITS
    ftagPool
    0.90
    setVerticalGroup
    0.90
    SequentialGroup
    0.88
    TagMode
    0.87
    XmlAccessorType
    0.79
    IUrlHelper
    0.78
    脚注の使い方
    0.78
    HasForeignKey
    0.74
    出版年
    0.74
     raiſ
    0.73
    Activations Density 0.618%

    No Known Activations