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. 15456
    Prev
    Next
    INDEX
    Explanations

    content related to food reviews

    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
     betweenstory
    -0.76
     Italijanski
    -0.76
     المعيارى
    -0.73
    tagext
    -0.73
    StoryboardSegue
    -0.72
     незавершена
    -0.71
     فريبيس
    -0.66
    PullParser
    -0.66
     Мексичка
    -0.65
     <=",
    -0.65
    POSITIVE LOGITS
    tka
    0.53
    sendRedirect
    0.52
    <eos>
    0.49
     estrenar
    0.49
    webElementGuid
    0.49
     surla
    0.49
    ("")]
    0.44
     esi
    0.43
     Goldie
    0.43
     AssemblyTitle
    0.43
    Activations Density 0.300%

    No Known Activations