© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 375
    Prev
    Next
    INDEX
    Explanations

    the occurrence of backslashes in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ي
    -0.96
    adpleegd
    -0.81
     Ser
    -0.77
     esc
    -0.77
    Sucesor
    -0.77
     Сер
    -0.76
     Eagles
    -0.75
    ništvo
    -0.74
     Cay
    -0.74
     Esc
    -0.74
    POSITIVE LOGITS
    \
    1.22
    %\
    1.16
    ()\
    1.15
    ))\
    1.11
    #\
    1.02
     {}\
    0.99
    )\
    0.97
     /\.
    0.93
    ;\
    0.93
     "'");
    0.92
    Activations Density 0.219%

    No Known Activations