© 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. 2935
    Prev
    Next
    INDEX
    Explanations

    names of people and characters associated with prominent roles or events

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

    First part of certain last names

    np_acts-logits-general · gemini-2.0-flash

    celebrity names

    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
     et
    -0.51
     tider
    -0.48
    期間
    -0.47
     um
    -0.46
     successo
    -0.46
     the
    -0.45
     основном
    -0.43
     меньше
    -0.42
     a
    -0.41
     nyata
    -0.41
    POSITIVE LOGITS
    ⓧ
    0.91
     noDo
    0.83
     nahilalakip
    0.83
    ########.
    0.82
     actionMode
    0.80
     uParam
    0.79
    
    0.78
    abetes
    0.77
    AutoresizingMask
    0.77
     onAnimation
    0.77
    Activations Density 0.220%

    No Known Activations