© 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-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 2505
    Prev
    Next
    INDEX
    Explanations

    terms related to irrigation and irreducibility concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ondheim
    -0.42
     løpet
    -0.41
    utives
    -0.38
    hira
    -0.38
     Kirch
    -0.38
    getInstance
    -0.38
    berdayakan
    -0.37
    ByExample
    -0.37
     CIRCUIT
    -0.36
    mutlich
    -0.36
    POSITIVE LOGITS
    ir
    1.58
     Ir
    1.58
     ir
    1.54
    Ir
    1.46
     IR
    1.32
    IR
    1.13
     Irwin
    0.90
     irradiation
    0.89
     irri
    0.87
     Irvin
    0.86
    Activations Density 0.218%

    No Known Activations