© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4021
    Prev
    Next
    INDEX
    Explanations

    comparative and superlative adjectives indicating degree

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

    following intensifiers like "more", "very", "too"

    np_acts-logits-general · gemini-2.0-flash

    intensified descriptors

    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
     avoient
    -0.33
     gouvern
    -0.31
    的对象
    -0.25
    nameof
    -0.25
     ouv
    -0.23
    SerializeField
    -0.23
     medel
    -0.23
     éter
    -0.22
    yesterday
    -0.22
     jeter
    -0.22
    POSITIVE LOGITS
    ⟬
    0.87
    tagHelperRunner
    0.82
    niſſe
    0.75
    󠁣
    0.73
     ſans
    0.73
    ſicht
    0.72
    <unused41>
    0.71
    𑄮
    0.71
    [@BOS@]
    0.71
    <unused74>
    0.71
    Activations Density 0.400%

    No Known Activations