© 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. 4-GEMMASCOPE-RES-16K
    11. 15784
    Prev
    Next
    INDEX
    Explanations

    instances of the word "via."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bumb
    -0.68
     APL
    -0.62
    wness
    -0.62
     CCC
    -0.61
     SPH
    -0.60
    TST
    -0.60
     Hs
    -0.59
     Pn
    -0.59
    kkkk
    -0.57
     Mindy
    -0.57
    POSITIVE LOGITS
     via
    2.19
     Via
    2.00
    Via
    1.95
    via
    1.81
     VIA
    1.67
    VIA
    1.51
     tramite
    1.50
     vía
    1.38
     באמצעות
    1.23
     mittels
    1.23
    Activations Density 0.095%

    No Known Activations