© 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. 13402
    Prev
    Next
    INDEX
    Explanations

    criteria and specifics related to relationship intentions and requirements

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

    punctuation marks and sentence-ending periods.

    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
    Conclusie
    -0.37
    rawDesc
    -0.36
    autoreleasepool
    -0.35
    AxisAlignment
    -0.35
     prachtige
    -0.35
    incredible
    -0.35
     sahiptir
    -0.35
     XCTest
    -0.34
     deserved
    -0.33
     incredible
    -0.33
    POSITIVE LOGITS
     preferably
    2.20
     ideally
    2.13
     Preferably
    2.03
    preferably
    1.86
     Ideally
    1.86
    Ideally
    1.79
     preferable
    1.44
     ideal
    1.40
    Prefer
    1.40
     helst
    1.38
    Activations Density 0.568%

    No Known Activations