© 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. 14257
    Prev
    Next
    INDEX
    Explanations

    discussion of legal principles and considerations in a judicial context

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

    whitespace and formatting characters used 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
    SharedDtor
    -0.40
     كمان
    -0.36
     invokingState
    -0.35
     Fazit
    -0.35
    OGND
    -0.33
    protetor
    -0.33
    penup
    -0.31
     creatividad
    -0.30
     kommenden
    -0.30
    ➩
    -0.30
    POSITIVE LOGITS
    CodedInputStream
    0.54
     utafitiHapana
    0.52
    MethodManager
    0.51
     See
    0.50
    ResumeLayout
    0.50
    ագրություններ
    0.49
     Actually
    0.48
     Exacts
    0.48
    yntaxException
    0.47
    Actually
    0.47
    Activations Density 0.682%

    No Known Activations