© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 6104
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a basis or foundation for claims, arguments, or assumptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Симпто
    -0.52
    ventory
    -0.47
                                   
    -0.46
     jesús
    -0.44
    getTransaction
    -0.44
     vill
    -0.42
     tqdm
    -0.42
     mcqueen
    -0.42
     Vill
    -0.42
     parliament
    -0.42
    POSITIVE LOGITS
     based
    0.94
     BASED
    0.93
    based
    0.88
     Base
    0.88
     base
    0.86
    BASED
    0.85
    base
    0.83
     Based
    0.82
    Base
    0.81
     Basis
    0.79
    Activations Density 0.193%

    No Known Activations