© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 24197
    Prev
    Next
    INDEX
    Explanations

    phrases related to industry recognition and the impact of changes in market dynamics

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

    industry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    setVerticalGroup
    -0.50
    postIndex
    -0.46
    openConnection
    -0.45
    etCode
    -0.45
     villager
    -0.44
    UnusedPrivate
    -0.43
    riwal
    -0.43
    appartamento
    -0.42
     nakalista
    -0.42
    ExecuteReader
    -0.42
    POSITIVE LOGITS
     industry
    1.71
    industry
    1.52
    Industry
    1.45
     Industry
    1.38
     INDUSTRY
    1.28
     industria
    1.22
    行业
    1.20
    INDUSTRY
    1.19
     indústria
    1.17
    業界
    1.14
    Activations Density 0.060%

    No Known Activations