© 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. 18-GEMMASCOPE-RES-16K
    11. 75
    Prev
    Next
    INDEX
    Explanations

    the presence of forms of the verb "to be" in various tenses

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

    Followed by adjectives describing feelings or states of being

    np_acts-logits-general · gemini-2.0-flash

    is/was/were followed by adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omiya
    -0.56
     salido
    -0.46
     a
    -0.43
    belong
    -0.43
     belong
    -0.42
     come
    -0.42
    ngOnInit
    -0.41
     Belong
    -0.41
     belonging
    -0.41
    owned
    -0.41
    POSITIVE LOGITS
    tagHelperRunner
    1.00
    出版年
    0.91
     kaarangay
    0.86
     صوتيه
    0.82
    enderror
    0.76
    ValueStyle
    0.76
    Personendaten
    0.75
    Билгалдахарш
    0.70
     Roskov
    0.69
     pleased
    0.69
    Activations Density 0.378%

    No Known Activations