© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13724
    Prev
    Next
    INDEX
    Explanations

    instances of personal experiences or opinions expressed in a conversational context

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

    Follows first-person pronouns

    np_acts-logits-general · gemini-2.0-flash

    I followed by non-English word

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    expandindo
    -0.63
     gynhyrchwyd
    -0.63
    sizeCache
    -0.61
    DockStyle
    -0.57
    ItemBackground
    -0.56
    
    -0.56
     ujednoznacz
    -0.56
    #+#
    -0.56
     NSCoder
    -0.55
    Бахар
    -0.52
    POSITIVE LOGITS
     gelukkig
    0.37
     Opiniones
    0.36
     complains
    0.33
     written
    0.32
     Schmel
    0.32
    ***************
    0.32
     apunt
    0.31
     veille
    0.30
    Ptr
    0.30
     Furcht
    0.30
    Activations Density 0.147%

    No Known Activations