© 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. 20-GEMMASCOPE-RES-131K
    11. 23201
    Prev
    Next
    INDEX
    Explanations

    themes related to rebellion and conflict

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

    war and destruction

    np_acts-logits-general · gemini-2.5-flash-lite

    references to warfare, rebellion, and large-scale catastrophic domination or destruction events.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     &___
    -0.57
     disambiguazione
    -0.52
    ifikant
    -0.50
    MessageTagHelper
    -0.49
     Wikiseite
    -0.47
    AdapterFactory
    -0.46
     pieza
    -0.44
    tanleria
    -0.44
     surla
    -0.43
     GenerationType
    -0.43
    POSITIVE LOGITS
    PYX
    0.44
     اقت
    0.43
     war
    0.42
    aric
    0.42
     War
    0.42
     chaos
    0.41
     Us
    0.41
    habe
    0.40
    pog
    0.40
    krieg
    0.39
    Activations Density 0.109%

    No Known Activations