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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 8189
    Prev
    Next
    INDEX
    Explanations

    terms related to genetic material, particularly DNA, including its structure, modifications, and analysis techniques

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

    DNA and related components (bases, nucleotides)

    np_acts-logits-general · gemini-2.0-flash

    DNA and RNA interactions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.73
    ⓧ
    -0.61
    ViewById
    -0.60
    fxml
    -0.55
    tadır
    -0.51
     vermelhas
    -0.51
    dojo
    -0.51
    Ferdin
    -0.51
     زر
    -0.51
     réserv
    -0.50
    POSITIVE LOGITS
     DNA
    1.18
    DNA
    0.96
     base
    0.96
     bases
    0.90
     nucleotides
    0.88
     nucleotide
    0.82
     Base
    0.77
     Bases
    0.75
    base
    0.74
     double
    0.72
    Activations Density 1.385%

    No Known Activations