© 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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 93337
    Prev
    Next
    INDEX
    Explanations

    references to "real-life" experiences or contexts

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

    real life or real world contexts

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    omenclature
    -0.50
    enschutzer
    -0.36
    merksamkeit
    -0.34
    Signatures
    -0.34
    roidery
    -0.34
    posables
    -0.33
     poética
    -0.32
     mı
    -0.32
     gạch
    -0.31
     complete
    -0.31
    POSITIVE LOGITS
    reality
    0.81
    Real
    0.80
     reality
    0.76
    real
    0.72
     IRL
    0.71
     realities
    0.70
    realistic
    0.69
     Real
    0.69
    REAL
    0.68
    Reality
    0.67
    Activations Density 0.008%

    No Known Activations