© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 39-GEMMASCOPE-RES-16K
    11. 1087
    Prev
    Next
    INDEX
    Explanations

    links to social media and other online platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    astify
    -0.59
     nahilalakip
    -0.58
    WriteTagHelper
    -0.54
    explanatory
    -0.52
     فريبيس
    -0.51
    سطس
    -0.50
    DockStyle
    -0.49
    hical
    -0.48
    MethodManager
    -0.48
    IsContent
    -0.47
    POSITIVE LOGITS
     Follow
    1.31
    Follow
    1.25
     follow
    1.22
     FOLLOW
    1.20
    follow
    1.06
    FOLLOW
    0.99
     Visit
    0.98
     Subscribe
    0.96
     visit
    0.92
     Facebook
    0.92
    Activations Density 0.324%

    No Known Activations