© 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. 2-GEMMASCOPE-RES-16K
    11. 8663
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Sal" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleaſure
    -0.80
     Theſe
    -0.77
     Houſe
    -0.76
     CURIAM
    -0.76
     ſever
    -0.73
     cauſe
    -0.73
     purpoſe
    -0.72
     Shakspeare
    -0.71
     Chaldean
    -0.70
     Tert
    -0.70
    POSITIVE LOGITS
     Sal
    3.84
     sal
    3.71
    Sal
    3.67
    sal
    3.23
     SAL
    2.94
    SAL
    2.74
     salted
    1.61
     SALV
    1.55
     Sala
    1.54
     sali
    1.54
    Activations Density 0.033%

    No Known Activations