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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 53625
    Prev
    Next
    INDEX
    Explanations

    present forms of the verb "to be" and related auxiliary verbs in various contexts within the text

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

    dependence, perform, get, obtain, occur

    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
     Мексичка
    -0.56
     CreateTagHelper
    -0.55
     nahilalakip
    -0.49
     <=",
    -0.40
     reação
    -0.40
    Pranala
    -0.39
     Италијани
    -0.39
    ]-->
    -0.39
     ویکی‌پدی
    -0.38
     lunak
    -0.37
    POSITIVE LOGITS
     Kapol
    0.44
    ✭✭
    0.41
     macrop
    0.40
     voort
    0.40
    uang
    0.40
    PARATUS
    0.40
    SpringBootTest
    0.40
    Parker
    0.39
    transQ
    0.39
    letta
    0.39
    Activations Density 0.033%

    No Known Activations