© 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. 14220
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional vulnerability and human connection

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

    exaggeration or strong emotion

    np_acts-logits-general · gemini-2.0-flash

    live, breath, sleep and eat

    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
    ผล
    -0.35
     wspól
    -0.34
    PhysRevLett
    -0.34
     mniej
    -0.34
    较为
    -0.34
     responsabilità
    -0.34
    wnież
    -0.34
     secteur
    -0.34
     identitas
    -0.32
     agak
    -0.31
    POSITIVE LOGITS
     ویکی‌پدی
    0.70
     Савезне
    0.63
    rizona
    0.63
     Мексичка
    0.63
     Infórmanos
    0.61
    OGND
    0.59
     препратки
    0.58
     oprot
    0.58
     contextLoads
    0.56
    VersionUID
    0.55
    Activations Density 0.307%

    No Known Activations