Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 1617
    Prev
    Next
    INDEX
    Explanations

    instances of the word "but."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPATH
    -0.51
    min
    -0.51
    Hentet
    -0.50
    håll
    -0.49
    opsida
    -0.49
    seamnă
    -0.45
    bodyParser
    -0.45
     Australie
    -0.45
    Toro
    -0.45
     Adnan
    -0.45
    POSITIVE LOGITS
    findpost
    0.89
     아니라
    0.71
    だけでなく
    0.63
     cherchés
    0.61
     sonder
    0.60
    而且
    0.59
    principalColumn
    0.58
    だけではなく
    0.57
     bahkan
    0.57
    ungere
    0.56
    Activations Density 0.243%

    No Known Activations