© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3585
    Prev
    Next
    INDEX
    Explanations

    references to eyewitness accounts and testimonies

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

    witness testimony and eyewitness accounts in legal documents.

    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
    tagHelperRunner
    -0.60
    Jereo
    -0.55
     resourceCulture
    -0.54
     autorytatywna
    -0.53
    Autoritní
    -0.52
    IUrlHelper
    -0.51
     nakalista
    -0.48
    XmlAccessorType
    -0.47
    انيف
    -0.47
    Viited
    -0.47
    POSITIVE LOGITS
     witnesses
    2.06
     witness
    1.98
     eyewitness
    1.84
    Witnesses
    1.73
     Witnesses
    1.70
    witness
    1.70
     Witness
    1.66
     eyew
    1.66
    Witness
    1.65
     testigos
    1.62
    Activations Density 0.603%

    No Known Activations