© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 11007
    Prev
    Next
    INDEX
    Explanations

    occurrences of the verb "be" and its variations in context

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

    "be" followed by an adjective or location

    np_acts-logits-general · gemini-2.0-flash

    be followed by verb or adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '))
    -0.51
    Luv
    -0.50
    ândia
    -0.49
    OSIS
    -0.48
     gangen
    -0.47
    rapport
    -0.47
     umid
    -0.46
    다고
    -0.45
     traduce
    -0.45
    "):
    -0.45
    POSITIVE LOGITS
    出版年
    0.95
    RTEE
    0.73
    dafx
    0.73
    Autoritní
    0.70
     صوتيه
    0.68
    таратура
    0.67
    WriteTagHelper
    0.65
    躇
    0.64
    XtraGrid
    0.63
    TagMode
    0.62
    Activations Density 0.073%

    No Known Activations