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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 1940
    Prev
    Next
    INDEX
    Explanations

    terms related to data transfer and transmission processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Népesség
    -0.92
    FailureListener
    -0.91
    sizeCache
    -0.86
     Chwiliwch
    -0.83
     AssemblyCulture
    -0.82
    سطس
    -0.81
    
    -0.81
     IndexError
    -0.81
     Firms
    -0.81
    كويكب
    -0.80
    POSITIVE LOGITS
    Trans
    1.24
    trans
    1.24
     trans
    1.24
     transf
    1.23
     Trans
    1.18
    TRANS
    1.13
     TRANS
    1.12
     TRAN
    1.11
     transfers
    1.10
    strans
    1.06
    Activations Density 0.115%

    No Known Activations