© 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. 1758
    Prev
    Next
    INDEX
    Explanations

    references to unisex bathrooms and related discussions

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

    Non-English question words

    np_acts-logits-general · gemini-2.0-flash

    titles, categories, and descriptions

    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
     JpaRepository
    -0.72
     MainAxisSize
    -0.68
    abestanden
    -0.67
     insuffisamment
    -0.63
    stdarg
    -0.61
     HasFactory
    -0.60
    TextWatcher
    -0.60
    PMailer
    -0.59
     المعيارى
    -0.56
     bParam
    -0.56
    POSITIVE LOGITS
    How
    0.90
     How
    0.87
    how
    0.80
     how
    0.79
    如何
    0.78
    关于
    0.70
     untitled
    0.68
     چگونه
    0.68
    怎样
    0.67
    详解
    0.65
    Activations Density 0.235%

    No Known Activations