© 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-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 3289
    Prev
    Next
    INDEX
    Explanations

    instances of the word "since" and related expressions indicating causality or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vaux
    -0.66
    showConfirm
    -0.52
     Mazar
    -0.52
     thác
    -0.51
    pergillus
    -0.49
    createServer
    -0.48
     nodeId
    -0.48
     moulin
    -0.47
     message
    -0.47
    UnusedPrivate
    -0.46
    POSITIVE LOGITS
    Because
    0.98
    Karena
    0.95
    скольку
    0.93
    Since
    0.92
    由于
    0.91
    ieważ
    0.90
     Karena
    0.90
     karena
    0.89
    چون
    0.89
     متعلقه
    0.89
    Activations Density 0.209%

    No Known Activations