© 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. 1-GEMMASCOPE-RES-16K
    11. 3072
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the word "been."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    例文帳に追加
    -0.40
     malheur
    -0.38
    före
    -0.38
    gesetz
    -0.37
    tox
    -0.37
    odacty
    -0.37
     having
    -0.36
    ṟ
    -0.36
    Ultimately
    -0.35
    agner
    -0.35
    POSITIVE LOGITS
     been
    3.25
    been
    2.50
    Been
    2.34
     BEEN
    2.31
     Been
    2.31
     été
    1.59
     geweest
    1.52
     sido
    1.44
     vært
    1.41
     været
    1.35
    Activations Density 0.181%

    No Known Activations