© 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. 6640
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms related to materials and their applications in electronics

    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
     excru
    -0.52
     Propag
    -0.47
    存于互联网档案馆
    -0.44
    antası
    -0.43
    LEncoder
    -0.43
    Obfuscated
    -0.41
    addGroup
    -0.40
    propag
    -0.40
    ніципа
    -0.40
    Geplaatst
    -0.39
    POSITIVE LOGITS
     photo
    0.76
     photovoltaic
    0.71
    photo
    0.69
     Photo
    0.67
     solar
    0.67
    Photo
    0.66
     PHOTO
    0.60
     efficiency
    0.59
     fotovolta
    0.58
    Solar
    0.57
    Activations Density 0.758%

    No Known Activations