© 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. 4079
    Prev
    Next
    INDEX
    Explanations

    annotations and metadata related to database entities and their configurations

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

    Code-related special characters

    np_acts-logits-general · gemini-2.0-flash

    programming and code structure

    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
     للمعارف
    -0.61
     referenties
    -0.59
    OGND
    -0.52
     препратки
    -0.51
    endphp
    -0.51
    afficheront
    -0.49
    lardır
    -0.48
     متعلقه
    -0.46
     كومونز
    -0.46
     przecież
    -0.46
    POSITIVE LOGITS
    ":"",
    0.68
    TintMode
    0.63
    jfree
    0.63
     Мексичка
    0.60
    ISME
    0.60
     ReSharper
    0.59
    "",
    0.59
    #![
    0.58
     BoxDecoration
    0.58
    prefixer
    0.58
    Activations Density 0.031%

    No Known Activations