© 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. 6822
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of people and organizations

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

    Follows a capital letter

    np_acts-logits-general · gemini-2.0-flash

    proper names and initialisms

    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
    bootstrapcdn
    -0.79
     سكانية
    -0.64
    OGND
    -0.62
     المعيارى
    -0.61
     مشين
    -0.57
    parsedMessage
    -0.56
     وتسجيلات
    -0.55
    UnsafeEnabled
    -0.55
    intios
    -0.55
    ContentAsync
    -0.54
    POSITIVE LOGITS
    $_['
    0.60
    djangoproject
    0.54
    ziplin
    0.53
    حوالہ
    0.53
    المراجع
    0.52
    reactstrap
    0.51
    vernote
    0.51
     actionMode
    0.50
    怎么了
    0.50
     Bandcamp
    0.50
    Activations Density 0.806%

    No Known Activations