© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 34-GEMMASCOPE-RES-16K
    11. 6460
    Prev
    Next
    INDEX
    Explanations

    topics related to criticism and scrutiny of actions or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jalá
    -0.47
    ніципалі
    -0.44
     akad
    -0.38
    éndolo
    -0.37
     Picchu
    -0.36
    ờ
    -0.35
     sob
    -0.35
     Statistik
    -0.35
    égorie
    -0.35
    
    -0.34
    POSITIVE LOGITS
     received
    0.75
    來自
    0.69
    来自
    0.67
     reç
    0.66
     recib
    0.66
    received
    0.63
     coming
    0.59
     incoming
    0.58
    Received
    0.57
     Received
    0.57
    Activations Density 0.449%

    No Known Activations