© 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-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 9481
    Prev
    Next
    INDEX
    Explanations

    instances of doubt and references to emotional states or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -0.89
    ')['
    -0.77
    __":
    -0.69
    AutoresizingMask
    -0.68
    makeConstraints
    -0.60
    alnız
    -0.59
    avía
    -0.59
    rašymas
    -0.57
    พาะ
    -0.57
    stdc
    -0.57
    POSITIVE LOGITS
     never
    1.12
    never
    1.12
     Never
    1.11
     jamás
    1.11
    NEVER
    1.10
    Never
    1.10
     jamais
    1.04
     NEVER
    1.03
     nunca
    0.96
     nooit
    0.90
    Activations Density 0.122%

    No Known Activations