© 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-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 11194
    Prev
    Next
    INDEX
    Explanations

    references to gene expression and related biological data in experimental contexts

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

    Differentially expressed genes

    np_acts-logits-general · gemini-2.0-flash

    differentially expressed and regulated genes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Carriera
    -0.66
    ButterKnife
    -0.64
    曖昧さ回避
    -0.60
    Enders
    -0.59
    mappedBy
    -0.58
    mobileqq
    -0.58
     NSCoder
    -0.57
    riterion
    -0.54
    coroutines
    -0.54
     pinulongan
    -0.54
    POSITIVE LOGITS
     transcrip
    0.61
     microarray
    0.59
    Transcrip
    0.57
     identified
    0.55
     vulgaires
    0.54
     differentially
    0.54
    insatz
    0.52
     genes
    0.51
     annotated
    0.49
     enrich
    0.48
    Activations Density 2.027%

    No Known Activations