© 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. 37-GEMMASCOPE-RES-16K
    6. 5264
    Prev
    Next
    INDEX
    Explanations

    advice and recommendations related to personal and professional improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mxArray
    -0.38
    Rhestr
    -0.35
    Біографія
    -0.35
    WritableDatabase
    -0.34
    basicConfig
    -0.34
    IBAction
    -0.32
    于是
    -0.32
    TagHelper
    -0.32
    Kariera
    -0.30
     così
    -0.30
    POSITIVE LOGITS
     don
    1.95
     DON
    1.48
     Don
    1.48
    Don
    1.45
    don
    1.41
     jangan
    1.35
     DONT
    1.34
     remember
    1.32
     dont
    1.30
     Jangan
    1.28
    Activations Density 0.647%

    No Known Activations