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. 11-GEMMASCOPE-RES-16K
    6. 1788
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols used in formatting and coding

    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
     Efq
    -1.13
     itſelf
    -0.99
     themſelves
    -0.96
     raiſ
    -0.95
     Monfieur
    -0.95
     doubtnut
    -0.95
     ſeveral
    -0.94
     pleaſure
    -0.94
     uſed
    -0.93
     myſelf
    -0.93
    POSITIVE LOGITS
     /
    1.14
     Rosenthal
    0.93
    :✨
    0.87
     Mathis
    0.85
     /\
    0.84
     -
    0.84
     <<
    0.84
    iwa
    0.82
     /=
    0.82
     ->
    0.82
    Activations Density 0.334%

    No Known Activations