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
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 11372
    Prev
    Next
    INDEX
    Explanations

    technical concepts related to electronics and circuitry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lightboxes
    -0.52
    Trama
    -0.48
     CanadaChoose
    -0.46
     ब्रेकडाउन
    -0.45
     macchina
    -0.45
     kapturem
    -0.45
    ylvan
    -0.44
     Dure
    -0.44
    ecture
    -0.44
     disperse
    -0.44
    POSITIVE LOGITS
     amplifiers
    0.66
     amplifier
    0.66
     circuit
    0.64
     circuits
    0.60
     preamp
    0.59
     amplification
    0.57
     circuitry
    0.54
     Verstär
    0.53
     amplificador
    0.53
    amp
    0.52
    Activations Density 0.886%

    No Known Activations