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. 20-GEMMASCOPE-RES-131K
    6. 29573
    Prev
    Next
    INDEX
    Explanations

    genetic elements that encode proteins and their associated functions

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

    gene encoding proteins

    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
     AssemblyCulture
    -0.70
    NameInMap
    -0.63
    principalColumn
    -0.55
     Autorizaciones
    -0.53
    tagHelperRunner
    -0.52
    StructEnd
    -0.51
     Վերցված
    -0.51
    yakarta
    -0.50
    Rujuakan
    -0.50
    CodedInputStream
    -0.50
    POSITIVE LOGITS
    edan
    0.34
    JScrollPane
    0.34
    Osob
    0.32
    μι
    0.30
    "]();
    0.30
    Cubit
    0.30
    ConstraintMaker
    0.30
     defaultstate
    0.29
    jewództ
    0.29
    SequentialGroup
    0.29
    Activations Density 0.461%

    No Known Activations