Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 5206
    Prev
    Next
    INDEX
    Explanations

    sequences or patterns of symbols, particularly those involving backslashes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    triangleq
    -0.86
    ي
    -0.80
     يتيمه
    -0.78
     Goldberg
    -0.78
     Acosta
    -0.77
    elang
    -0.76
     Balt
    -0.76
    ypos
    -0.74
    adpleegd
    -0.74
    jdt
    -0.73
    POSITIVE LOGITS
    ))\
    1.34
    \
    1.24
    ?\
    1.23
    ;\
    1.18
    %\
    1.18
    );\
    1.15
     \\\
    1.15
    ).\
    1.14
     {}\
    1.10
    })\
    1.10
    Activations Density 0.044%

    No Known Activations