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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 2726
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming environments or libraries

    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
    Бахар
    -0.75
    IUrlHelper
    -0.72
    المشاركات
    -0.66
     المعيارى
    -0.66
    </thead>
    -0.64
    Toponymie
    -0.64
    ChildScrollView
    -0.59
     validamos
    -0.59
    Bronnen
    -0.59
     RemoteException
    -0.58
    POSITIVE LOGITS
    ✨
    0.97
    ✨:
    0.96
    ✨✨
    0.87
     ✨
    0.84
    :✨
    0.84
    LabelTagHelper
    0.65
     NSCoder
    0.60
     виправивши
    0.60
     Renaissance
    0.59
    __))
    0.58
    Activations Density 0.007%

    No Known Activations