© 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. 27
    Prev
    Next
    INDEX
    Explanations

    legal and procedural references related to rights and communications

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

    phrases describing someone taking action to help or assist another person with a specific task or goal.

    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
    ).__
    -0.34
    __":
    -0.33
     disambiguazione
    -0.31
     gillar
    -0.31
    PYX
    -0.29
    期刊论文
    -0.29
     чек
    -0.29
     Lexer
    -0.29
     démocratie
    -0.29
    junit
    -0.28
    POSITIVE LOGITS
     arranged
    1.85
     arrange
    1.84
     arranging
    1.84
     arrangements
    1.77
     arranges
    1.74
    arrange
    1.69
     Arrange
    1.63
    arranged
    1.61
     ARRANG
    1.60
     Arrangements
    1.59
    Activations Density 0.562%

    No Known Activations