© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 8616
    Prev
    Next
    INDEX
    Explanations

    references to speeches and addresses, particularly those made by political figures

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

    public speaking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ángeles
    -0.39
     marié
    -0.39
     CreateTagHelper
    -0.39
     engagé
    -0.33
    AddWithValue
    -0.33
     licencias
    -0.32
     Lightboxes
    -0.32
    rrggbb
    -0.31
     Lingkungan
    -0.31
     अलावा
    -0.31
    POSITIVE LOGITS
     speech
    0.92
     speeches
    0.88
     Speeches
    0.83
    peech
    0.77
     Speech
    0.76
    speech
    0.75
    Speech
    0.72
     '\\;'
    0.67
     SPEECH
    0.65
     discurso
    0.61
    Activations Density 0.035%

    No Known Activations