© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 6867
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific disciplines, particularly those involving biology and the life sciences

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

    science and its fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ripar
    -0.41
    นิ
    -0.39
     soprav
    -0.33
     cliquant
    -0.33
     안
    -0.32
     itself
    -0.32
    ][-
    -0.32
    раздо
    -0.31
     Rtl
    -0.31
     wikipagina
    -0.31
    POSITIVE LOGITS
    ciences
    2.33
    cience
    2.33
     Biosciences
    1.08
    cienti
    0.99
    ciencia
    0.98
    SCIENCE
    0.96
     Conscience
    0.90
     conscience
    0.87
    cien
    0.81
    cientific
    0.80
    Activations Density 0.047%

    No Known Activations