© 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. 9835
    Prev
    Next
    INDEX
    Explanations

    references to names or specific terminology associated with identity and culture

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

    ending in "ast," "ist," or "est."

    np_acts-logits-general · gemini-2.0-flash

    'ast' or 'est' endings

    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
     الدولى
    -1.00
    aarrggbb
    -0.89
    出版年
    -0.86
     Meksiku
    -0.86
    Rohy
    -0.84
    rrggbb
    -0.84
    SpringBootTest
    -0.83
    клопе
    -0.82
     Duggan
    -0.81
    endphp
    -0.80
    POSITIVE LOGITS
    bst
    0.69
    AST
    0.68
    BAST
    0.66
    Est
    0.66
     pst
    0.65
    ast
    0.64
     NST
    0.64
    ost
    0.64
     OST
    0.63
    est
    0.63
    Activations Density 0.423%

    No Known Activations