Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 13897
    Prev
    Next
    INDEX
    Explanations

    terms related to consent and ethical approval in research studies

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

    "Consent" or "request" preceding a verb

    np_acts-logits-general · gemini-2.0-flash

    consent form

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    writeFieldEnd
    -0.52
     movimenti
    -0.50
    PreferredItem
    -0.50
     nemici
    -0.48
     viewDidLoad
    -0.47
    ipelago
    -0.47
     affari
    -0.46
     vostri
    -0.45
    Accessibility
    -0.45
     popoli
    -0.45
    POSITIVE LOGITS
     sheet
    1.24
     sheets
    1.18
     Sheet
    1.04
     letter
    1.03
     Sheets
    1.00
     paperwork
    0.96
     forms
    0.93
     document
    0.93
     SHEET
    0.93
    heet
    0.93
    Activations Density 0.719%

    No Known Activations