© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 15734
    Prev
    Next
    INDEX
    Explanations

    indicators of quantity or availability

    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
    SharedCtor
    -0.47
    tanleria
    -0.43
    WriteTagHelper
    -0.38
    toThrow
    -0.36
    labelledby
    -0.32
    issimo
    -0.32
    gnore
    -0.32
    glVertex
    -0.30
    IFORN
    -0.30
    MediaStore
    -0.30
    POSITIVE LOGITS
     remaining
    3.30
     Remaining
    2.91
    remaining
    2.84
    Remaining
    2.70
     leftover
    2.31
     остав
    2.23
    剩余
    2.06
     restante
    2.05
     restantes
    2.02
     residual
    1.98
    Activations Density 1.096%

    No Known Activations