© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 2538
    Prev
    Next
    INDEX
    Explanations

    terms related to narratives of conflict and resolution

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

    preceding types of battles

    np_acts-logits-general · gemini-2.0-flash

    combat and battles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     opérateur
    -0.52
    RTLD
    -0.52
     disambiguazione
    -0.49
     StatelessWidget
    -0.49
     réforme
    -0.48
    gatsby
    -0.47
    kloped
    -0.46
     كومونز
    -0.46
    Aspiration
    -0.46
     Савезне
    -0.46
    POSITIVE LOGITS
     battle
    2.51
     fight
    2.34
     battles
    2.29
     fighting
    2.11
    battle
    2.09
     fights
    2.07
     fought
    2.04
    fight
    2.02
     battling
    1.95
     Battle
    1.88
    Activations Density 0.408%

    No Known Activations