© 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. 16-GEMMASCOPE-RES-16K
    11. 14584
    Prev
    Next
    INDEX
    Explanations

    sections or headings related to "Introduction"

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

    "Introduction" or section headings

    np_acts-logits-general · gemini-2.0-flash

    section introductions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.83
    хьтан
    -0.82
    ffindor
    -0.81
    /-/
    -0.75
     Bioaccumulative
    -0.75
     AssemblyVersion
    -0.71
     springfox
    -0.71
    )";
    -0.70
    λευτα
    -0.69
     ?>/
    -0.68
    POSITIVE LOGITS
    tvguidetime
    0.63
    rungsseite
    0.56
    ंदीखरीदारी
    0.54
     متعلقه
    0.53
     برانيه
    0.52
    prüche
    0.51
    parsedMessage
    0.51
    ISupport
    0.50
    SharedCtor
    0.48
     estimés
    0.46
    Activations Density 0.383%

    No Known Activations