Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 53551
    Prev
    Next
    INDEX
    Explanations

    instances of clinical practice or training in medical contexts

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

    performed actions and tasks

    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
     opérateurs
    -0.44
     ailes
    -0.43
     contribución
    -0.43
     keluarganya
    -0.42
     käyttö
    -0.41
     inspección
    -0.41
     violación
    -0.41
     puntuación
    -0.41
     importación
    -0.40
     sostenibilidad
    -0.40
    POSITIVE LOGITS
    Хьажоргаш
    0.52
     gynhyrchwyd
    0.48
     weird
    0.45
    seido
    0.44
     CreateTagHelper
    0.44
     '{@
    0.44
     fud
    0.44
    localctx
    0.43
     handouts
    0.43
     condes
    0.42
    Activations Density 0.040%

    No Known Activations