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-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 10658
    Prev
    Next
    INDEX
    Explanations

    terms related to legal processes and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -1.18
     ainfi
    -1.08
     themſelves
    -1.04
     ſtate
    -1.03
     Monfieur
    -1.01
     Houſe
    -0.99
     Reſ
    -0.99
     purpoſe
    -0.98
     Theſe
    -0.96
     Efq
    -0.96
    POSITIVE LOGITS
     
    0.83
     or
    0.69
     in
    0.66
     and
    0.62
     very
    0.61
     has
    0.55
     a
    0.55
     l
    0.54
     an
    0.54
     A
    0.54
    Activations Density 0.737%

    No Known Activations