© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 14693
    Prev
    Next
    INDEX
    Explanations

    references to salivary functions and related dysfunctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kendrick
    -0.65
     DUB
    -0.63
     برانيه
    -0.62
     Hend
    -0.60
     TextAppearance
    -0.60
    Hend
    -0.56
     VizieR
    -0.56
     quæ
    -0.56
     Auvergne
    -0.56
     Condor
    -0.56
    POSITIVE LOGITS
     Sal
    2.86
     sal
    2.86
    Sal
    2.81
     SAL
    2.75
    sal
    2.64
    SAL
    2.55
     salt
    2.38
     Salt
    2.15
     salted
    2.09
    salt
    2.08
    Activations Density 0.434%

    No Known Activations