© 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. 12368
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "we" and its variations, indicating a focus on collective or inclusive statements

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

    starts of common phrases

    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
    principalTable
    -0.41
    Hozzáférés
    -0.36
     recevrez
    -0.35
     """",
    -0.35
    OptionsMenu
    -0.35
    Xna
    -0.34
     NPY
    -0.33
    

    -0.33
     تضيفلها
    -0.32
    地看着
    -0.32
    POSITIVE LOGITS
    ðsíða
    0.64
    clerView
    0.54
     Walkover
    0.53
    bricas
    0.51
    majánló
    0.50
    encils
    0.50
    xFFFFFF
    0.49
    技
    0.48
    iſen
    0.47
    sprüng
    0.46
    Activations Density 0.022%

    No Known Activations