© 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. 20-GEMMASCOPE-RES-16K
    11. 10410
    Prev
    Next
    INDEX
    Explanations

    object property definitions and their attributes in programming-related contexts

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

    Followed by "we", "are", or other common words

    np_acts-logits-general · gemini-2.0-flash

    court originally, cytokines are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    -0.62
    ,
    -0.58
    <eos>
    -0.52
    -
    -0.51
    ↵↵
    -0.51
    ar
    -0.48
    @
    -0.47
    <strong>
    -0.46
     
    -0.46
    ing
    -0.43
    POSITIVE LOGITS
    ſelves
    0.97
    AndEndTag
    0.96
     saites
    0.94
    .",
    0.94
    SPATH
    0.93
     ſind
    0.92
     $_"
    0.92
    ſelf
    0.92
    ]));
    0.91
    .}~\
    0.91
    Activations Density 0.066%

    No Known Activations