© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 15
    Prev
    Next
    INDEX
    Explanations

    specific genetic elements and markers in biological texts

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

    genomic coordinates and gene features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     NSCoder
    -0.78
    évaluateur
    -0.72
     AssemblyTitle
    -0.72
    UserScript
    -0.71
    expandindo
    -0.70
     CreateTagHelper
    -0.69
    AndEndTag
    -0.68
    Personendaten
    -0.65
     '\\;'
    -0.65
    ########.
    -0.65
    POSITIVE LOGITS
     sp
    0.41
     
    0.35
     per
    0.34
     pri
    0.34
    par
    0.32
     ro
    0.32
    para
    0.32
     bat
    0.31
     mas
    0.31
     relevant
    0.31
    Activations Density 0.176%

    No Known Activations