© 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. 3-GEMMASCOPE-RES-16K
    6. 5306
    Prev
    Next
    INDEX
    Explanations

    terms related to various types of 'actors' or 'actuators' used in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.57
     الرياضيه
    -0.51
     cherchés
    -0.48
     stří
    -0.48
    PerformLayout
    -0.46
    DebuggerNonUser
    -0.45
     auroit
    -0.45
     betweenstory
    -0.43
     ब्रेकडाउन
    -0.43
    Existence
    -0.43
    POSITIVE LOGITS
    ator
    1.40
    ators
    1.07
    ATOR
    1.05
    ador
    0.78
    atorul
    0.73
    atora
    0.72
    ATORS
    0.71
    adores
    0.68
    atori
    0.66
    atoren
    0.63
    Activations Density 1.316%

    No Known Activations