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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 5929
    Prev
    Next
    INDEX
    Explanations

    email addresses and associated identifiers

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

    Initials followed by "@" or a domain

    np_acts-logits-general · gemini-2.0-flash

    email addresses and urls

    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
     CreateTagHelper
    -0.67
    TIMORE
    -0.64
    neapolis
    -0.61
    ########.
    -0.61
    DeleteBehavior
    -0.61
    aliyun
    -0.60
     محفوظة
    -0.58
    HttpFoundation
    -0.58
    ruptedException
    -0.57
     stik
    -0.56
    POSITIVE LOGITS
     willi
    0.51
    wohl
    0.49
    _
    0.47
     MCS
    0.47
    matchCondition
    0.46
     violins
    0.45
    coste
    0.44
     Roskov
    0.44
    \_
    0.43
    czaj
    0.43
    Activations Density 0.383%

    No Known Activations