Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 23-GEMMASCOPE-RES-16K
    6. 12362
    Prev
    Next
    INDEX
    Explanations

    technical specifications and features of electronic devices, particularly audio equipment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GraphicsUnit
    -1.03
     defaultstate
    -0.95
    DockStyle
    -0.95
    ंदीखरीदारी
    -0.90
    Geplaatst
    -0.87
    WriteBarrier
    -0.84
    __(/*!
    -0.83
    setVerticalGroup
    -0.83
    WriteTagHelper
    -0.83
    AutoresizingMask
    -0.82
    POSITIVE LOGITS
     adopts
    0.66
     multifunctional
    0.51
     Widely
    0.50
    &
    0.49
     Colorful
    0.49
    Applicable
    0.49
     adopt
    0.49
     thickened
    0.48
     Adopted
    0.47
    Feature
    0.47
    Activations Density 0.108%

    No Known Activations