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. 9-GEMMASCOPE-RES-131K
    6. 58300
    Prev
    Next
    INDEX
    Explanations

    words related to vascular or circulatory systems, particularly those containing "ular" or "vascular"

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

    words ending in ular

    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
    Andi
    -0.48
     hospice
    -0.47
     Üniversitesi
    -0.46
    Accreditation
    -0.45
     Embaj
    -0.45
    Hoff
    -0.45
    IfNot
    -0.44
     aspi
    -0.44
     recompensa
    -0.44
     hoff
    -0.44
    POSITIVE LOGITS
    ular
    2.61
    ULAR
    1.98
    cular
    1.43
    icular
    1.20
     ular
    1.15
    ularia
    1.09
    ricular
    1.03
    bular
    1.01
    ticular
    0.99
    ilar
    0.98
    Activations Density 0.027%

    No Known Activations