© 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
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5154
    Prev
    Next
    INDEX
    Explanations

    travel-related terms, particularly referring to transportation and locations

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

    transportation-related words and travel descriptions involving modes of transportation like planes, buses, boats, and travel routes.

    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
     ModelExpression
    -0.56
    AndEndTag
    -0.54
    ValueStyle
    -0.48
    RotationOrder
    -0.45
    rician
    -0.45
    ftagPool
    -0.44
    exterior
    -0.44
    nezeu
    -0.43
    NESSEE
    -0.43
     Privacidad
    -0.43
    POSITIVE LOGITS
     arriving
    0.52
     flights
    0.47
    jsonwebtoken
    0.45
     arrive
    0.43
     flown
    0.43
     arrived
    0.42
    GEBURTSDATUM
    0.42
     transported
    0.41
     arrives
    0.41
     Arri
    0.41
    Activations Density 0.100%

    No Known Activations