© 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. 18-GEMMASCOPE-RES-16K
    11. 4066
    Prev
    Next
    INDEX
    Explanations

    phrases related to cellular processes and experimental procedures

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

    "...was/were suspended/resuspended in..."

    np_acts-logits-general · gemini-2.0-flash

    suspended, resuspended, added, frozen

    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
     riuscito
    -0.54
    portál
    -0.52
    ürm
    -0.52
    nvarchar
    -0.50
     Special
    -0.47
     epis
    -0.47
     ricordi
    -0.47
    mybatisplus
    -0.46
    (&_
    -0.45
    Edición
    -0.45
    POSITIVE LOGITS
    tvguidetime
    0.62
    Rujuakan
    0.57
     nắp
    0.56
    awtextra
    0.56
     الرياضيه
    0.56
     resus
    0.54
    masing
    0.54
    ViewFeatures
    0.54
     Administrativna
    0.54
    HtmlAttribute
    0.53
    Activations Density 1.119%

    No Known Activations