© 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. 40-GEMMASCOPE-RES-16K
    11. 5351
    Prev
    Next
    INDEX
    Explanations

    references to specific places, particularly restaurants and eateries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PSE
    -0.27
     ALR
    -0.25
    :][
    -0.23
     metrów
    -0.23
     __(
    -0.23
     OGS
    -0.23
     proced
    -0.23
    —(
    -0.22
     IFT
    -0.21
     GSP
    -0.21
    POSITIVE LOGITS
    co
    0.73
    cor
    0.70
    mor
    0.70
    len
    0.70
    dex
    0.69
    will
    0.69
    bol
    0.69
    wil
    0.69
    mac
    0.69
    col
    0.68
    Activations Density 0.792%

    No Known Activations