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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12743
    Prev
    Next
    INDEX
    Explanations

    mathematical inequalities and expressions involving subsets and limitations

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

    Less than sign

    np_acts-logits-general · gemini-2.0-flash

    less than comparisonor comparison symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    ValueStyle
    -0.54
    RTEE
    -0.52
    ształ
    -0.48
    SourceChecksum
    -0.42
     lắng
    -0.41
    nesium
    -0.41
    хіво
    -0.41
    큼
    -0.40
    节
    -0.40
    oneofs
    -0.39
    POSITIVE LOGITS
    ≺
    0.54
    }<
    0.53
    }<\
    0.52
     $<
    0.51
     (<
    0.48
    lesssim
    0.48
    ="<
    0.47
    ]<
    0.47
    ()<
    0.47
    '<
    0.46
    Activations Density 0.588%

    No Known Activations