© 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. 928
    Prev
    Next
    INDEX
    Explanations

    numerical values and measurements related to power, weight, and size

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

    Units of measurement

    np_acts-logits-general · gemini-2.0-flash

    units of measurement and magnitude

    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
     يتيمه
    -0.85
     doubtnut
    -0.76
    sterious
    -0.74
    ſelves
    -0.74
    ANTLR
    -0.71
     oprot
    -0.71
    ChildScrollView
    -0.71
     Archiproducts
    -0.71
     BoxDecoration
    -0.71
     Normdatei
    -0.70
    POSITIVE LOGITS
     per
    0.80
     or
    0.70
     total
    0.62
    左右
    0.62
     minimum
    0.62
     तक
    0.59
     apiece
    0.58
     maximum
    0.57
    以上
    0.56
     of
    0.56
    Activations Density 0.887%

    No Known Activations