© 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. 13-GEMMASCOPE-RES-16K
    6. 9029
    Prev
    Next
    INDEX
    Explanations

    references to ordinal indicators such as "first," "second," "third," "fourth," "fifth," etc

    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
     oprot
    -0.45
     båda
    -0.45
     sekitarnya
    -0.43
    ionales
    -0.43
     pamamagitan
    -0.41
    voorbeeld
    -0.41
     früheren
    -0.41
    tură
    -0.40
     przesz
    -0.40
    ๆ
    -0.40
    POSITIVE LOGITS
     third
    0.84
     fifth
    0.81
    third
    0.79
    fifth
    0.78
     fourth
    0.77
     Third
    0.74
    Third
    0.74
    fourth
    0.73
    Fifth
    0.69
     sixth
    0.66
    Activations Density 0.439%

    No Known Activations