© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13803
    Prev
    Next
    INDEX
    Explanations

    references to environments that promote positive or negative experiences, particularly in healthcare or social contexts

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

    "environment" or "atmosphere"

    np_acts-logits-general · gemini-2.0-flash

    environment and atmosphere

    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
    MessageOf
    -0.63
    kijken
    -0.56
     getItemId
    -0.56
     متعلقه
    -0.56
     OFDb
    -0.54
     UserDao
    -0.54
     tajam
    -0.53
    immortal
    -0.53
     getInt
    -0.52
     geſch
    -0.52
    POSITIVE LOGITS
     environment
    1.07
     environments
    0.86
     ambiente
    0.83
     atmosphere
    0.79
     Umgebung
    0.77
     entorno
    0.77
     ENVIRONMENT
    0.76
     entornos
    0.76
     ortam
    0.76
     surroundings
    0.76
    Activations Density 0.406%

    No Known Activations