© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 12244
    Prev
    Next
    INDEX
    Explanations

    code snippets related to user interface elements and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.87
     تضيفلها
    -0.79
     <=",
    -0.66
     invokingState
    -0.65
    ReusableCell
    -0.65
     AttributeSet
    -0.64
    GEBURTSDATUM
    -0.63
     فريبيس
    -0.63
     AssemblyCulture
    -0.63
    GOTREF
    -0.63
    POSITIVE LOGITS
    -(
    0.64
     -(
    0.53
    AnchorStyles
    0.52
     fortsatt
    0.51
     tunggal
    0.51
     genomen
    0.48
    AccessorTable
    0.47
    +(
    0.46
     -
    0.45
     női
    0.45
    Activations Density 0.169%

    No Known Activations