© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1344
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical research and patient treatment considerations

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

    after question words ("what", "how", etc.)

    np_acts-logits-general · gemini-2.0-flash

    medical and scientific contexts

    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
    enumii
    -0.47
     bezeichneter
    -0.44
    Gizmos
    -0.42
    afficheront
    -0.40
    BufferException
    -0.37
    🦵
    -0.37
     bParam
    -0.36
    wpdb
    -0.35
    arraycopy
    -0.35
    InSection
    -0.35
    POSITIVE LOGITS
    <?
    0.60
     AssemblyVersion
    0.53
     متعلقه
    0.52
    WithIOException
    0.48
    complexContent
    0.47
     afectan
    0.46
    RTLR
    0.42
    parsedMessage
    0.41
    CloseOperation
    0.40
     fermés
    0.40
    Activations Density 0.981%

    No Known Activations