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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4702
    Prev
    Next
    INDEX
    Explanations

    references to scientific studies and their findings

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

    technical terminology and data-related vocabulary across different domains like medical research, programming, and scientific writing.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    OGND
    -0.82
     Normdatei
    -0.68
    writeFieldEnd
    -0.67
    DockStyle
    -0.66
    :✨
    -0.63
     فريبيس
    -0.62
    󠁣
    -0.60
    __*/
    -0.59
     ***!
    -0.59
    GEBURTS
    -0.59
    POSITIVE LOGITS
    uxxxx
    1.92
    weightedMode
    0.81
     MemoryStream
    0.65
     editText
    0.61
    InstrumentedTest
    0.60
    .*")]
    0.59
    InjectAttribute
    0.58
    numeros
    0.40
     pobres
    0.35
     Luar
    0.35
    Activations Density 1.465%

    No Known Activations