© 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. 99597
    Prev
    Next
    INDEX
    Explanations

    positive sentiments and expressions of admiration

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

    user turns

    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
    
    -0.85
    httphttps
    -0.83
     ***!
    -0.82
    دانشنامهٔ
    -0.82
    Хьажоргаш
    -0.81
    ########.
    -0.80
    GEBURTS
    -0.79
    Personendaten
    -0.77
    原始内容存档于
    -0.77
     kasarigan
    -0.77
    POSITIVE LOGITS
    warnai
    0.27
     Ane
    0.27
    yych
    0.27
     похо
    0.25
     exactly
    0.25
    defi
    0.25
    veld
    0.24
     garden
    0.24
    self
    0.24
    Ane
    0.24
    Activations Density 0.013%

    No Known Activations