© 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. 2969
    Prev
    Next
    INDEX
    Explanations

    references to legal terms and discussions

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

    Code, numbers, and non-English text

    np_acts-logits-general · gemini-2.0-flash

    special characters, code snippets, or technical terms

    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
     CreateTagHelper
    -0.97
     AssemblyCulture
    -0.94
    Personendaten
    -0.80
    setVerticalGroup
    -0.79
     ProtoMessage
    -0.79
    RenderAtEndOf
    -0.79
     arşivlendi
    -0.76
    SharedDtor
    -0.73
     للاسماء
    -0.70
     ―――――
    -0.70
    POSITIVE LOGITS
    وعة
    0.46
     kérdés
    0.41
    klassen
    0.41
     것이다
    0.41
     spécialisée
    0.41
    RepeatedField
    0.40
    addCriterion
    0.40
    insatz
    0.40
     поводу
    0.39
     tzw
    0.39
    Activations Density 0.112%

    No Known Activations