© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2210
    Prev
    Next
    INDEX
    Explanations

    references to situational failures or conditions that imply distress or challenge

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

    Punctuation, code, and conversational fragments

    np_acts-logits-general · gemini-2.0-flash

    religious affiliation or history

    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
     Ephe
    -0.81
     المعيارى
    -0.80
    ########.
    -0.79
    存于互联网档案馆
    -0.79
    出版年
    -0.76
    abestanden
    -0.70
    Revenir
    -0.67
     GIP
    -0.67
     Rhetor
    -0.66
     PRD
    -0.66
    POSITIVE LOGITS
    ,
    0.91
    .
    0.81
     and
    0.70
     –
    0.64
     The
    0.62
    깐
    0.62
    /
    0.61
    ;
    0.58
    :
    0.58
    ↵↵
    0.56
    Activations Density 0.632%

    No Known Activations