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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1644
    Prev
    Next
    INDEX
    Explanations

    structured data formats, particularly related to JSON-like entries

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

    JSON structures involving the word "title"

    np_acts-logits-general · gemini-2.0-flash

    JSON parsing and code constructs

    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
     meilleurs
    -0.51
    errHandler
    -0.49
    </i>
    -0.48
    using
    -0.46
    totta
    -0.45
     Lindberg
    -0.45
    mergeFrom
    -0.45
     récentes
    -0.44
     העולם
    -0.44
     ausgewä
    -0.44
    POSITIVE LOGITS
     Roskov
    0.71
     متعلقه
    0.69
     مرئيه
    0.68
     Seeder
    0.61
     jScrollPane
    0.61
    )":
    0.61
     Audiodateien
    0.60
    CompleteListener
    0.59
    "$
    0.59
    makeConstraints
    0.57
    Activations Density 0.571%

    No Known Activations