© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 12568
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences with family and parenting

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

    Possessive pronouns followed by a relationship word

    np_acts-logits-general · gemini-2.0-flash

    family and friends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    曖昧さ回避
    -0.50
    ngrx
    -0.44
     besky
    -0.40
    стоин
    -0.40
    UTIVE
    -0.40
    锆
    -0.40
     quelconque
    -0.40
    rrggbb
    -0.39
    umably
    -0.39
    还有什么
    -0.39
    POSITIVE LOGITS
     coworker
    0.54
    EndInit
    0.52
     fiancée
    0.50
     college
    0.50
     townhouse
    0.50
     niece
    0.49
     roommate
    0.49
     girlfriend
    0.49
     boyfriend
    0.48
     interstate
    0.48
    Activations Density 0.553%

    No Known Activations