© 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. 105331
    Prev
    Next
    INDEX
    Explanations

    key figures and their roles in political processes and investigations

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

    DDT Tillerson Kelly memo

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    expandindo
    -0.68
    ロウィン
    -0.65
    tvguidetime
    -0.61
     لينك
    -0.55
     rhestr
    -0.54
    𑄮
    -0.54
     ब्रेकडाउन
    -0.53
     utafitiHapana
    -0.52
    AnchorTagHelper
    -0.52
    <unused41>
    -0.52
    POSITIVE LOGITS
    SpringRunner
    0.37
     cose
    0.36
    Демографія
    0.35
    Bibliograf
    0.34
    Personensuche
    0.34
     avenir
    0.33
    MongoClient
    0.32
    WriteBarrier
    0.32
     pleaſure
    0.31
    SpringBootTest
    0.30
    Activations Density 0.068%

    No Known Activations