© 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. 46749
    Prev
    Next
    INDEX
    Explanations

    phrases indicating needs and recommendations, particularly in technological or scientific contexts

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

    this is why

    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
    évaluateur
    -0.49
     however
    -0.48
     entanto
    -0.46
     insuffisamment
    -0.45
     však
    -0.43
    ceğini
    -0.42
    WaitGroup
    -0.42
     <<<<<<<<<<<<<<
    -0.42
     jedoch
    -0.41
     azonban
    -0.41
    POSITIVE LOGITS
     Administrativna
    0.50
    Personensuche
    0.47
     meg
    0.43
     nameof
    0.43
     mega
    0.43
    MessageOf
    0.42
     disambiguazione
    0.42
    InternalFrame
    0.39
     onPause
    0.39
    OGND
    0.38
    Activations Density 0.090%

    No Known Activations