© 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. 199
    Prev
    Next
    INDEX
    Explanations

    phrases related to memorials and historical references

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

    preceding a verb of existence

    np_acts-logits-general · gemini-2.0-flash

    there is a

    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
     <<<<<<<<<<<<<<
    -0.61
    enterOuterAlt
    -0.58
     ujednoznacz
    -0.53
    CPtr
    -0.53
    featureID
    -0.52
    putExtra
    -0.52
    jsonwebtoken
    -0.51
    出版年
    -0.51
     disambiguazione
    -0.51
    ClientSize
    -0.49
    POSITIVE LOGITS
     lies
    1.36
     there
    1.27
     comes
    1.10
     sits
    1.08
     are
    1.02
     resides
    1.02
     exists
    1.00
    there
    0.96
     lays
    0.92
     lie
    0.91
    Activations Density 0.273%

    No Known Activations