© 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. 22-GEMMASCOPE-RES-16K
    11. 5641
    Prev
    Next
    INDEX
    Explanations

    coding syntax and structure related to styling and component rendering

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

    Code snippets or markup

    np_acts-logits-general · gemini-2.0-flash

    correctly predicts diagram/code constructs

    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
     '\\;'
    -0.85
    SupportActionBar
    -0.72
    estacks
    -0.70
     propOrder
    -0.66
     سكانية
    -0.66
    ChildScrollView
    -0.65
    Cyfarwyddwr
    -0.65
     собі
    -0.63
    лтамалар
    -0.63
     виправивши
    -0.63
    POSITIVE LOGITS
    formik
    0.54
     jala
    0.52
    OGND
    0.52
    <%=
    0.52
     Waldorf
    0.51
    (&:
    0.51
    __(/*!
    0.50
     props
    0.50
    !</
    0.50
     Bodega
    0.49
    Activations Density 0.013%

    No Known Activations