© 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. 8657
    Prev
    Next
    INDEX
    Explanations

    formal elements of professional communication and reports

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

    formal document structure and professional correspondence formatting (salutations, attachments, and standard letter elements).

    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
    ClientRect
    -0.46
    spoken
    -0.44
     betweenstory
    -0.42
    jsonwebtoken
    -0.42
    DMETHOD
    -0.40
     Gallimard
    -0.40
     BoxDecoration
    -0.40
    Portail
    -0.40
    OGND
    -0.40
    lgica
    -0.40
    POSITIVE LOGITS
     attached
    2.31
     Attached
    2.08
    Attached
    2.00
    attached
    1.97
     enclosed
    1.97
     attach
    1.81
     Enclosed
    1.70
     attachment
    1.65
     attaching
    1.65
     attachments
    1.62
    Activations Density 0.509%

    No Known Activations