© 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
    7. Residual Stream - 16k
    9. 13-GEMMASCOPE-RES-16K
    11. 7980
    Prev
    Next
    INDEX
    Explanations

    references to houses or homes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CppMethod
    -0.60
    횟
    -0.59
    DataAnnotations
    -0.56
    retudo
    -0.55
     OMITTED
    -0.52
     futile
    -0.50
    ؜
    -0.50
    tidal
    -0.49
    nambuco
    -0.48
    kiat
    -0.48
    POSITIVE LOGITS
     house
    1.60
     House
    1.55
    House
    1.51
     HOUSE
    1.47
    house
    1.39
     houses
    1.24
    HOUSE
    1.23
     Houses
    1.23
     Houſe
    1.14
     hous
    1.10
    Activations Density 0.050%

    No Known Activations