© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15848
    Prev
    Next
    INDEX
    Explanations

    references to individual biographical details

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

    biographical information and professional credentials sections.

    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
    Produzione
    -0.49
    WebControls
    -0.47
    Населення
    -0.46
     estekak
    -0.45
    hoeddwyd
    -0.44
    yakarta
    -0.38
     kaarangay
    -0.37
    嚷
    -0.37
    醐
    -0.36
     VizieR
    -0.35
    POSITIVE LOGITS
     bio
    2.34
     biography
    2.28
     biographical
    2.09
     biographies
    2.02
    bio
    1.97
     Biography
    1.96
     Bio
    1.95
     BIO
    1.84
    Biography
    1.83
     био
    1.82
    Activations Density 0.332%

    No Known Activations