© 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. 20-GEMMASCOPE-RES-16K
    11. 15356
    Prev
    Next
    INDEX
    Explanations

    code structure elements, particularly class and method definitions in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets or syntax

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions with psi

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WithIdentifier
    -0.61
    \{\\
    -0.61
     odds
    -0.59
     hashCode
    -0.54
    DockStyle
    -0.54
    出版年
    -0.52
    Odds
    -0.51
     enx
    -0.50
    YLON
    -0.49
    odds
    -0.49
    POSITIVE LOGITS
     esternos
    0.67
    UnusedPrivate
    0.61
     GenerationType
    0.57
    Bibliograf
    0.55
    Geplaatst
    0.53
    </blockquote>
    0.50
    WithIOException
    0.49
     وتسجيلات
    0.49
     AssemblyTitle
    0.48
    Sinopse
    0.45
    Activations Density 0.049%

    No Known Activations