© 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. 5-GEMMASCOPE-RES-16K
    11. 7075
    Prev
    Next
    INDEX
    Explanations

    terms related to involvement or participation in processes or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /
    -0.55
     creatine
    -0.54
    H
    -0.53
    G
    -0.52
    ņas
    -0.52
    h
    -0.51
     dată
    -0.49
    P
    -0.49
     المعيارى
    -0.49
     and
    -0.48
    POSITIVE LOGITS
    AnchorStyles
    1.11
    ✨:
    1.03
     autorytatywna
    1.03
    volves
    1.03
    DockStyle
    1.01
    ineno
    1.00
    tonode
    1.00
     encompass
    0.96
     encompasses
    0.96
     INCLUDES
    0.95
    Activations Density 0.813%

    No Known Activations