© 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. 4849
    Prev
    Next
    INDEX
    Explanations

    phrases related to requirements, regulations, and necessary conditions in various contexts

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

    sequences describing prerequisites, requirements, or necessary conditions that must be fulfilled.

    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
    useful
    -0.50
    ✭✭
    -0.48
    helpful
    -0.45
     helpful
    -0.44
     membantu
    -0.44
    easily
    -0.42
    Easily
    -0.42
     unwittingly
    -0.41
    pecabe
    -0.40
     dzięki
    -0.40
    POSITIVE LOGITS
    才行
    1.13
    才能
    1.13
    才可以
    0.84
     lest
    0.82
     inorder
    0.80
    才會
    0.73
     иначе
    0.71
     else
    0.69
    しないと
    0.68
     Otherwise
    0.67
    Activations Density 0.548%

    No Known Activations