© 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. 2-GEMMASCOPE-RES-16K
    11. 7120
    Prev
    Next
    INDEX
    Explanations

    keywords related to scientific research methodologies

    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
    förs
    -0.54
     esternos
    -0.51
     pouvoit
    -0.47
     provocation
    -0.45
     pleaſure
    -0.45
     juſ
    -0.45
     ſche
    -0.44
     confirmation
    -0.44
     dismissal
    -0.44
    şekkür
    -0.43
    POSITIVE LOGITS
     investigated
    2.11
     examined
    2.08
     studied
    2.08
     analyzed
    1.90
     surveyed
    1.89
     analysed
    1.85
    examined
    1.78
     tested
    1.76
    studied
    1.72
     Studied
    1.71
    Activations Density 0.357%

    No Known Activations