© 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. 5466
    Prev
    Next
    INDEX
    Explanations

    the beginning of a document

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

    Tokens after numbers

    np_acts-logits-general · gemini-2.0-flash

    Richard Broun

    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
    WriteBarrier
    -0.76
    ⓘ
    -0.70
     autorytatywna
    -0.67
    SourceChecksum
    -0.61
     insuffisamment
    -0.61
    izr
    -0.57
    سمبر
    -0.57
    /*
    -0.56
    zeera
    -0.56
    :✨
    -0.55
    POSITIVE LOGITS
    Geplaatst
    0.57
    DebuggerNonUser
    0.55
     culturelle
    0.51
    давно
    0.49
    állítás
    0.47
    ViewChild
    0.47
    DebuggerStep
    0.47
    riwal
    0.45
     voici
    0.45
    httphttps
    0.45
    Activations Density 0.479%

    No Known Activations