© 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. 24-GEMMASCOPE-RES-16K
    11. 4782
    Prev
    Next
    INDEX
    Explanations

    language related to governmental policies and criticism of energy companies

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

    Political parties or actors

    np_acts-logits-general · gemini-2.0-flash

    political parties and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -0.98
     виправивши
    -0.78
     beginnetje
    -0.74
     resourceCulture
    -0.66
    DeleteBehavior
    -0.66
    abestanden
    -0.64
    windowFixed
    -0.63
    MLLoader
    -0.62
    ActionCreators
    -0.62
    ResumeLayout
    -0.62
    POSITIVE LOGITS
     Tory
    0.90
    Tory
    0.87
     Tories
    0.83
     Labour
    0.76
     Ministers
    0.75
     ministers
    0.75
     councils
    0.74
     councillors
    0.72
    consultation
    0.71
    Labour
    0.71
    Activations Density 0.344%

    No Known Activations