© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 6572
    Prev
    Next
    INDEX
    Explanations

    references to competing interests and states related to user interface control

    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
     незавершена
    -1.17
     Italijani
    -1.17
     تضيفلها
    -1.15
    Geplaatst
    -1.14
    writeFieldEnd
    -1.12
     Himo
    -1.11
     Signalez
    -1.09
     Италијани
    -1.06
     EClass
    -1.04
    AsUp
    -1.03
    POSITIVE LOGITS
    DebuggerNonUser
    0.63
    </strong>
    0.57
     
    0.54
    </b>
    0.48
    <eos>
    0.46
    </u>
    0.45
    </em>
    0.45
     [
    0.40
    ,
    0.40
     to
    0.40
    Activations Density 0.006%

    No Known Activations