© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 533
    Prev
    Next
    INDEX
    Explanations

    text related to process efficiency, particularly focusing on installation challenges and costs associated with device assembly

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

    Follows conjunctions/transition words

    np_acts-logits-general · gemini-2.0-flash

    technical code and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    المناصب
    -0.39
    verwijspagina
    -0.33
    homes
    -0.30
     jspb
    -0.30
    ună
    -0.29
     consectetur
    -0.29
     eri
    -0.28
     Luzern
    -0.28
     Homes
    -0.28
    ZERO
    -0.28
    POSITIVE LOGITS
    IntoConstraints
    0.65
    EndContext
    0.58
     kasarigan
    0.57
    RectangleBorder
    0.57
    SpringBootTest
    0.54
     AssemblyTitle
    0.53
    writeFieldEnd
    0.52
    __).
    0.52
    istoitu
    0.52
     Lightboxes
    0.52
    Activations Density 0.630%

    No Known Activations