© 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. 22-GEMMASCOPE-RES-16K
    11. 8224
    Prev
    Next
    INDEX
    Explanations

    issues related to gameplay mechanics and character interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    after "be" (is, are, was, were)

    np_acts-logits-general · gemini-2.0-flash

    balance and nerf

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.59
    entieth
    -0.54
    costal
    -0.52
    pédie
    -0.51
     Aurelius
    -0.50
    Mentions
    -0.47
     TextEditing
    -0.45
    이버
    -0.44
    rhosis
    -0.44
     ucha
    -0.44
    POSITIVE LOGITS
     balance
    1.07
     nerfed
    1.04
     nerf
    1.01
     balancing
    1.00
     balanced
    0.94
    balance
    0.94
     unbalanced
    0.93
    balancing
    0.92
     Balance
    0.90
     nerfs
    0.88
    Activations Density 0.167%

    No Known Activations