© 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. 2-GEMMASCOPE-RES-16K
    11. 4785
    Prev
    Next
    INDEX
    Explanations

    references to the term "hard."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    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
    -0.44
    PreInfinity
    -0.43
    wość
    -0.35
    GEBURTS
    -0.35
    věr
    -0.32
     kasarigan
    -0.31
    GOTREF
    -0.30
    siede
    -0.30
     spout
    -0.29
    ται
    -0.29
    POSITIVE LOGITS
     hard
    4.31
     Hard
    3.89
    Hard
    3.84
    hard
    3.73
     HARD
    3.39
    HARD
    3.33
     harder
    2.91
     hardest
    2.66
     harde
    2.59
     hård
    2.55
    Activations Density 0.092%

    No Known Activations