© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 15917
    Prev
    Next
    INDEX
    Explanations

    elements related to judicial proceedings and legal arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Formatting/layout tags (HTML)

    np_acts-logits-general · gemini-2.0-flash

    HTML paragraph and list markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.79
     iconFacebook
    -0.72
    +#+#
    -0.72
    protoc
    -0.71
    WebServlet
    -0.70
    зулта
    -0.70
    PathVariable
    -0.69
    ManagedBean
    -0.69
     AssemblyVersion
    -0.69
    OGND
    -0.68
    POSITIVE LOGITS
    ↵↵
    0.53
    <tr>
    0.50
     الحره
    0.46
     Consequently
    0.44
    ämä
    0.42
     Nevertheless
    0.41
     apo
    0.41
    Nonetheless
    0.41
    .\\
    0.39
     setLoading
    0.39
    Activations Density 0.185%

    No Known Activations