Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9145
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and expressions of opinion or uncertainty

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

    First-person perspective

    np_acts-logits-general · gemini-2.0-flash

    first person statements

    np_acts-logits-general · gemini-2.5-flash-lite

    personal, subjective statements that use first- (and often second-) person pronouns to express opinions, experiences, or direct address

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    complexContent
    -0.68
    ſelf
    -0.65
     ExecuteAsync
    -0.65
    
    -0.65
    RenderAtEndOf
    -0.61
    bootstrapcdn
    -0.59
    WireFormatLite
    -0.57
    providedIn
    -0.56
     AssemblyProduct
    -0.56
    期刊论文
    -0.56
    POSITIVE LOGITS
     azt
    0.29
     kyllä
    0.28
     believe
    0.28
     hundert
    0.27
     π
    0.26
     löytyy
    0.26
     creemos
    0.26
     am
    0.25
     heard
    0.25
    以
    0.25
    Activations Density 0.399%

    No Known Activations