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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3076
    Prev
    Next
    INDEX
    Explanations

    references to gut-related biological functions and immune responses

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

    Intestinal lining and related terms

    np_acts-logits-general · gemini-2.0-flash

    intestinal mucosa and epithelium

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Personendaten
    -0.48
     Roskov
    -0.44
    Definition
    -0.44
     aikaa
    -0.43
    ckså
    -0.43
    Herkunft
    -0.42
     wireType
    -0.40
     Numerade
    -0.38
    fromnode
    -0.38
    Tembelea
    -0.38
    POSITIVE LOGITS
    helial
    0.63
     epithelial
    0.57
     intestinal
    0.56
     mucosal
    0.56
     Barrier
    0.53
     barrier
    0.53
     epithelium
    0.50
    Barrier
    0.49
    epithe
    0.49
    barrier
    0.49
    Activations Density 0.945%

    No Known Activations