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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4013
    Prev
    Next
    INDEX
    Explanations

    significant mentions of dissent or opposition to plans and policies

    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
     می‌شوند
    -0.43
    檚
    -0.38
     бъдат
    -0.38
    ksyon
    -0.38
     شوند
    -0.36
     serem
    -0.36
     become
    -0.36
    become
    -0.35
     thermique
    -0.34
     były
    -0.34
    POSITIVE LOGITS
     believe
    1.51
     think
    1.34
     want
    1.34
     expect
    1.29
     hope
    1.27
     feel
    1.25
    believe
    1.16
     wish
    1.16
     appreciate
    1.13
     intend
    1.13
    Activations Density 0.842%

    No Known Activations