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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 10553
    Prev
    Next
    INDEX
    Explanations

    technical terms related to biochemical processes and experimental methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IndentedString
    -0.84
     كومونز
    -0.79
    ReusableCell
    -0.75
    QMetaType
    -0.72
    NewUrlParser
    -0.67
    xase
    -0.67
     BoxDecoration
    -0.66
    borderSide
    -0.66
     gebou
    -0.65
     للمعارف
    -0.65
    POSITIVE LOGITS
    vic
    0.57
    AccessFile
    0.56
    lev
    0.55
     دار
    0.53
    ances
    0.53
     garganta
    0.52
    gradient
    0.51
     Gradient
    0.50
    Interop
    0.48
     dev
    0.48
    Activations Density 1.877%

    No Known Activations