© 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. 31-GEMMASCOPE-RES-16K
    11. 15998
    Prev
    Next
    INDEX
    Explanations

    historical references or notable inventions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    historical facts about the invention and origins of consumer products and technologies.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cheeky
    -0.55
    ampunk
    -0.54
     immersive
    -0.52
     unsustainable
    -0.51
    fjspx
    -0.51
    gamesh
    -0.50
     EMEA
    -0.50
    dfunding
    -0.50
    intervention
    -0.50
     DSLR
    -0.50
    POSITIVE LOGITS
     مشين
    0.41
    MigrationBuilder
    0.40
     specialmente
    0.39
     thiệu
    0.38
     sécurité
    0.38
    Попис
    0.37
    دانشنامهٔ
    0.37
     spécialisé
    0.37
     carpeta
    0.37
     automáticamente
    0.36
    Activations Density 0.524%

    No Known Activations