© 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. 31-GEMMASCOPE-RES-16K
    11. 2249
    Prev
    Next
    INDEX
    Explanations

    references to significant historical events and their impacts

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

    the word "the" appearing before nouns that describe abstract concepts, developments, or characteristics.

    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
     insuffisamment
    -0.68
    principalColumn
    -0.62
    RectangleBorder
    -0.61
     gynhyrchwyd
    -0.59
     CreateTagHelper
    -0.59
    Хьажоргаш
    -0.57
    FormState
    -0.56
     виправивши
    -0.56
     whatever
    -0.55
     الحره
    -0.55
    POSITIVE LOGITS
     significance
    0.95
     origins
    0.90
     meaning
    0.90
     reasons
    0.86
     importance
    0.85
     impact
    0.84
     role
    0.81
     implications
    0.80
     origin
    0.75
     rationale
    0.74
    Activations Density 0.576%

    No Known Activations