© 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. 36-GEMMASCOPE-RES-16K
    11. 9652
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to neural networks and their architectures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fjspx
    -0.57
    CodeAttribute
    -0.50
    SequentialGroup
    -0.50
     yyr
    -0.47
    ScopeManager
    -0.45
     BoxFit
    -0.44
    Архівовано
    -0.43
     endforeach
    -0.43
    TargetException
    -0.43
    MemoryWarning
    -0.42
    POSITIVE LOGITS
     input
    3.30
     Input
    2.89
     inputs
    2.84
    input
    2.83
    Input
    2.70
     INPUT
    2.69
     Inputs
    2.53
    INPUT
    2.50
    输入
    2.38
    inputs
    2.27
    Activations Density 1.124%

    No Known Activations