© 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. 14262
    Prev
    Next
    INDEX
    Explanations

    quotes and reports from political figures

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

    Statements or quotes given to the press

    np_acts-logits-general · gemini-2.0-flash

    telling reporters

    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
    UserScript
    -0.68
    ContentLoaded
    -0.61
     igång
    -0.59
    WebElementEntity
    -0.59
    osoma
    -0.57
    fjspx
    -0.57
    didSet
    -0.56
    }))
    -0.56
     jScrollPane
    -0.55
    PerformLayout
    -0.55
    POSITIVE LOGITS
     reporters
    1.45
     press
    1.06
     reporter
    0.90
     pressed
    0.88
     interviewer
    0.85
     journalists
    0.84
    Pressed
    0.83
     presse
    0.82
    press
    0.82
     wartawan
    0.82
    Activations Density 0.132%

    No Known Activations