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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 92257
    Prev
    Next
    INDEX
    Explanations

    references to tissue and related concepts in biological and medical contexts

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

    tissue states and distributions

    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
    ⓧ
    -0.61
     OMITBAD
    -0.54
     nôtre
    -0.44
    SqlClient
    -0.42
    Cargar
    -0.42
    guió
    -0.42
     Komun
    -0.42
    primera
    -0.41
    Aholisi
    -0.41
    URLException
    -0.41
    POSITIVE LOGITS
     tissue
    1.08
     Tissue
    1.06
    Tissue
    1.04
    tissue
    0.97
     tissues
    0.96
     Tissues
    0.96
     tissus
    0.79
     tissu
    0.71
     Gewebe
    0.68
    tissu
    0.67
    Activations Density 0.022%

    No Known Activations