© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13357
    Prev
    Next
    INDEX
    Explanations

    phrases involving "to" followed by verbs or actions

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

    "to" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    much to show/offer/prove

    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
    ্ষ
    -0.53
    hel
    -0.48
    lit
    -0.47
     Reverso
    -0.47
    rager
    -0.45
     qualcosa
    -0.43
    ou
    -0.42
     chiave
    -0.42
     грн
    -0.42
    adpleegd
    -0.42
    POSITIVE LOGITS
     typelib
    1.07
     worry
    0.81
    worry
    0.78
    mybatisplus
    0.76
    anskje
    0.74
    spare
    0.73
     useParams
    0.71
    ratulations
    0.70
    KURZBESCHREIBUNG
    0.69
     spare
    0.68
    Activations Density 0.103%

    No Known Activations