© 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. 14232
    Prev
    Next
    INDEX
    Explanations

    elements associated with legal cases, citations, and specific names or terms in legal contexts

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

    proper nouns and names, particularly surnames and formal titles.

    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
     AssemblyTitle
    -0.44
     protoimpl
    -0.43
     AssemblyProduct
    -0.42
     rhestr
    -0.40
     faſt
    -0.40
    Hochspringen
    -0.40
     تضيفلها
    -0.39
    BeginInit
    -0.38
    ={<
    -0.38
     ब्रेकडाउन
    -0.37
    POSITIVE LOGITS
    WriteTagHelper
    0.53
    ⟬
    0.42
    ardless
    0.40
     pocz
    0.40
    PerformLayout
    0.39
     prawo
    0.38
    ignées
    0.36
    خدمات
    0.36
    accro
    0.35
     Nog
    0.35
    Activations Density 0.781%

    No Known Activations