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. 23-GEMMASCOPE-RES-16K
    6. 9346
    Prev
    Next
    INDEX
    Explanations

    references to databases and data management topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 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
     Monument
    -0.52
    ssy
    -0.47
     Simply
    -0.44
    ➌
    -0.44
     magie
    -0.44
    simply
    -0.44
     monument
    -0.43
     magi
    -0.42
    uggest
    -0.42
     Magic
    -0.42
    POSITIVE LOGITS
    новништво
    0.63
    elemField
    0.53
     Мексичка
    0.47
    errHandler
    0.46
    ChildScrollView
    0.41
    abestanden
    0.40
    MemoryWarning
    0.40
    verwijspagina
    0.40
    倒是
    0.37
     nahilalakip
    0.37
    Activations Density 0.907%

    No Known Activations