© 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. 97153
    Prev
    Next
    INDEX
    Explanations

    phrases and words that indicate negativity or negative impacts

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

    negative sentiment and effects

    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
    setEditable
    -0.40
     wystarczy
    -0.38
    commodations
    -0.38
     çift
    -0.38
     Bedarf
    -0.37
     begged
    -0.37
     semplici
    -0.37
    sidemargin
    -0.36
     sencillas
    -0.36
     transfieras
    -0.36
    POSITIVE LOGITS
    Negative
    0.76
     negativ
    0.75
     negativo
    0.73
     negative
    0.72
     Negative
    0.70
    NegativeButton
    0.69
    ThroughAttribute
    0.68
     kötü
    0.65
    Worst
    0.65
     negatively
    0.65
    Activations Density 0.076%

    No Known Activations