© 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. 24-GEMMASCOPE-RES-16K
    6. 4157
    Prev
    Next
    INDEX
    Explanations

    conjunctions in technical or formal contexts

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

    "And" followed by a list of items

    np_acts-logits-general · gemini-2.0-flash

    lists ending with etc

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnusedPrivate
    -0.73
    GraphicsUnit
    -0.71
     purpoſe
    -0.64
     laſt
    -0.60
     ſeveral
    -0.59
     myſelf
    -0.58
     poffible
    -0.57
     themſelves
    -0.57
    berdayakan
    -0.56
     uſed
    -0.56
    POSITIVE LOGITS
     other
    1.01
    other
    0.90
    etc
    0.85
     Other
    0.82
     etc
    0.78
     Etc
    0.78
     outros
    0.78
     …)
    0.77
     whatnot
    0.74
     autres
    0.73
    Activations Density 0.564%

    No Known Activations