© 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. 2-GEMMASCOPE-RES-16K
    11. 3471
    Prev
    Next
    INDEX
    Explanations

    patterns of numerical sequences or values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ので
    -0.73
    ))))
    -0.70
    ")==
    -0.65
    ))))))))
    -0.64
    alisa
    -0.64
    '))
    -0.64
    vms
    -0.63
    ))));
    -0.63
    letal
    -0.61
    bunt
    -0.61
    POSITIVE LOGITS
    8
    2.27
    9
    1.55
    7
    1.51
     Eighth
    1.36
     EIGHT
    1.36
     Eight
    1.32
    eight
    1.29
    6
    1.28
     Eighty
    1.23
    Eight
    1.22
    Activations Density 0.581%

    No Known Activations