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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 5809
    Prev
    Next
    INDEX
    Explanations

    biochemical interactions related to saliva and its properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedDtor
    -0.64
     nakalista
    -0.49
    Glej
    -0.42
    csname
    -0.41
    IsContent
    -0.40
    tanleria
    -0.40
     snippetHide
    -0.39
    enterOuterAlt
    -0.39
     recic
    -0.36
    getResultList
    -0.36
    POSITIVE LOGITS
     adsorption
    0.93
     adsor
    0.79
     interaction
    0.77
     adsorbed
    0.75
     interactions
    0.75
     Adsorption
    0.74
     sorption
    0.70
     binding
    0.68
     attachment
    0.68
     interact
    0.66
    Activations Density 2.054%

    No Known Activations