© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 11325
    Prev
    Next
    INDEX
    Explanations

    financial and economic indicators and their implications

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

    Financial/economic "rate" or "cut" mentions

    np_acts-logits-general · gemini-2.0-flash

    downgrades and rate cuts

    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
    HomeAsUpEnabled
    -0.69
    IntoConstraints
    -0.65
    yari
    -0.53
    vfill
    -0.51
    pédie
    -0.51
    SaveChangesAsync
    -0.50
    literals
    -0.49
    apunov
    -0.49
    WebpackPlugin
    -0.49
     giovan
    -0.49
    POSITIVE LOGITS
     downgrade
    0.83
     downgraded
    0.76
     upgraded
    0.75
     outlook
    0.73
     downg
    0.72
     upgrade
    0.71
    PerformLayout
    0.68
    Upgrade
    0.67
     revised
    0.66
     upgrades
    0.65
    Activations Density 0.127%

    No Known Activations