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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3769
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to statistical estimation

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

    estimation

    np_acts-logits-general · gemini-2.0-flash

    estimating or estimating values

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    flexDirection
    -0.50
    Behaviors
    -0.45
    SocketChannel
    -0.44
    fontFamily
    -0.43
     ChromeDriver
    -0.43
     obě
    -0.43
     nemlig
    -0.42
     spécialement
    -0.41
     FLUID
    -0.41
    pherals
    -0.41
    POSITIVE LOGITS
     estimate
    1.26
     Estimate
    1.19
    Estimate
    1.11
    estimate
    1.10
     estimation
    1.07
     estimates
    1.07
     Estimates
    1.01
     Estimation
    1.01
     estimating
    0.97
     estimations
    0.97
    Activations Density 0.273%

    No Known Activations