© 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-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 1349
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to data structure and programming logic

    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
    majánló
    -1.05
    gucig
    -0.99
     Italij
    -0.96
    ðsíða
    -0.94
     anún
    -0.89
    DockStyle
    -0.87
     dezelve
    -0.87
    genodigd
    -0.87
     Monfieur
    -0.87
     zelve
    -0.86
    POSITIVE LOGITS
     pec
    0.27
     pr
    0.26
     ta
    0.26
     nh
    0.25
     ub
    0.25
     wn
    0.24
     yp
    0.23
     Pr
    0.23
     tr
    0.23
     hir
    0.22
    Activations Density 0.771%

    No Known Activations