© 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 EvalsExportsinterp-engineNEWAPI 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. 7528
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate challenges or difficulties in a certain context

    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
     ujednoznacz
    -0.50
    Datuak
    -0.50
     MainAxisSize
    -0.48
    alitions
    -0.48
    ᐧ
    -0.48
     defaultstate
    -0.46
    IModel
    -0.45
    şört
    -0.44
     loginUser
    -0.44
    hyrchwyd
    -0.44
    POSITIVE LOGITS
     Compared
    0.78
    Compared
    0.72
    Meanwhile
    0.72
     Meanwhile
    0.71
    According
    0.66
    Moreover
    0.65
    Nowadays
    0.65
     compared
    0.64
     According
    0.64
    Through
    0.63
    Activations Density 0.753%

    No Known Activations