© 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. 15-GEMMASCOPE-RES-16K
    6. 856
    Prev
    Next
    INDEX
    Explanations

    sentences expressing opinions or subjective assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſtand
    -0.65
     jaunes
    -0.57
     ſte
    -0.56
    sidemargin
    -0.56
     ſche
    -0.55
     uſe
    -0.53
     ſtate
    -0.53
     myſelf
    -0.52
     ſta
    -0.51
     purpoſe
    -0.51
    POSITIVE LOGITS
    UnusedPrivate
    0.50
     a
    0.49
     it
    0.49
     المعيارى
    0.45
     درو
    0.44
    шло
    0.40
     fine
    0.40
     its
    0.40
     pretty
    0.40
     RVA
    0.39
    Activations Density 0.214%

    No Known Activations