© 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. 6-GEMMASCOPE-RES-16K
    11. 13119
    Prev
    Next
    INDEX
    Explanations

    formatting codes and comments typically found in software documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -0.67
    }{@
    -0.60
    tinggi
    -0.60
     Walkover
    -0.59
     nî
    -0.59
     ModelExpression
    -0.58
    YMMV
    -0.58
     NUKAT
    -0.58
     Frisch
    -0.58
    TAGE
    -0.57
    POSITIVE LOGITS
     Charlene
    0.58
    NamedQueries
    0.56
    Cubit
    0.54
    warf
    0.53
     Meksiku
    0.52
     Malden
    0.51
    %=
    0.50
    jboss
    0.49
     McP
    0.49
     couvre
    0.49
    Activations Density 0.273%

    No Known Activations