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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 2922
    Prev
    Next
    INDEX
    Explanations

    language related to estimation and approximation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    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
    -0.45
    fontFamily
    -0.45
    Brother
    -0.44
    Yeah
    -0.42
     participado
    -0.41
    SocketChannel
    -0.41
     nemlig
    -0.41
     functionally
    -0.40
    SqlSession
    -0.40
     emotionally
    -0.40
    POSITIVE LOGITS
     estimate
    1.64
     Estimate
    1.51
     estimates
    1.50
    Estimate
    1.42
    estimate
    1.41
     Estimates
    1.40
     estimation
    1.38
     estimated
    1.36
     estimating
    1.30
    estimates
    1.29
    Activations Density 0.321%

    No Known Activations