© 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. 201
    Prev
    Next
    INDEX
    Explanations

    structured sections or organization in written content

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

    Following words like "each" or "every"

    np_acts-logits-general · gemini-2.0-flash

    individually listed components

    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
    DebuggerStep
    -0.56
    BeginContext
    -0.54
     anything
    -0.52
    //
    -0.51
    ela
    -0.51
     hiç
    -0.51
     nowhere
    -0.51
     Anything
    -0.49
    lera
    -0.49
    UnknownFieldSet
    -0.49
    POSITIVE LOGITS
     individually
    1.39
     câte
    1.31
     einzeln
    1.25
     separately
    1.23
    씩
    1.03
    individ
    1.01
     independently
    0.93
    별
    0.91
     đều
    0.84
    獨立
    0.83
    Activations Density 0.273%

    No Known Activations