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-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15761
    Prev
    Next
    INDEX
    Explanations

    terms related to modification and modulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -1.00
     BIBSYS
    -0.95
     nakalista
    -0.94
     referenties
    -0.90
    تقاوى
    -0.90
    ')[
    -0.88
     Rockefeller
    -0.88
    lidene
    -0.88
     }}"></
    -0.88
    Viited
    -0.87
    POSITIVE LOGITS
    mod
    1.48
     Mod
    1.43
     mod
    1.35
    Mod
    1.30
    Mods
    1.25
     mods
    1.21
     modding
    1.06
     Mods
    1.05
    mods
    1.05
     modulator
    1.02
    Activations Density 0.088%

    No Known Activations