© 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. 9-GEMMASCOPE-RES-16K
    11. 10747
    Prev
    Next
    INDEX
    Explanations

    terms related to "hard" or difficult concepts, materials, and tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     IFTT
    -0.74
     виправивши
    -0.70
    PreInfinity
    -0.69
    exitRule
    -0.65
    GEBURTS
    -0.61
    LLocation
    -0.60
     fieldNum
    -0.59
     MainAxisSize
    -0.58
     kasarigan
    -0.57
     ModelExpression
    -0.57
    POSITIVE LOGITS
     hard
    2.30
     Hard
    2.23
    Hard
    2.19
    hard
    2.06
     HARD
    1.92
    HARD
    1.87
     harder
    1.61
     Harder
    1.46
     harde
    1.45
     hardest
    1.42
    Activations Density 0.078%

    No Known Activations