© 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. 1-GEMMASCOPE-RES-16K
    11. 9181
    Prev
    Next
    INDEX
    Explanations

    terms related to completion or results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.67
    сур
    -0.63
    iVar
    -0.54
    supset
    -0.53
    heça
    -0.52
     GenerationType
    -0.52
    oarece
    -0.51
     Coen
    -0.50
    '))
    -0.49
     humaine
    -0.49
    POSITIVE LOGITS
     finish
    4.29
     Finish
    3.99
    finish
    3.84
     FINISH
    3.71
    Finish
    3.66
     finishes
    3.56
    FINISH
    3.27
     finishing
    3.13
     finished
    3.12
     Finished
    3.00
    Activations Density 0.064%

    No Known Activations