© 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. 15406
    Prev
    Next
    INDEX
    Explanations

    references to measurements and evaluations in a technical or scientific context

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

    "In" followed by a prepositional phrase

    np_acts-logits-general · gemini-2.0-flash

    in the followed by sentences

    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
    ...
    -0.56
    …
    -0.55
     even
    -0.55
     adalah
    -0.48
     —
    -0.48
    دهی
    -0.47
     la
    -0.47
     res
    -0.47
     would
    -0.46
     Lav
    -0.46
    POSITIVE LOGITS
    +#+#
    0.90
     تضيفلها
    0.83
     AssemblyCompany
    0.76
    GEBURTSDATUM
    0.73
    HtmlAttribute
    0.72
    LookAnd
    0.66
    ArgsConstructor
    0.65
     препратки
    0.64
    StructEnd
    0.63
     كومونز
    0.62
    Activations Density 0.076%

    No Known Activations