© 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. 11268
    Prev
    Next
    INDEX
    Explanations

    corporate entities and legal contexts

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

    after company names

    np_acts-logits-general · gemini-2.0-flash

    German princes or Wallace names

    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
     VIAF
    -0.79
     AssemblyProduct
    -0.74
     médié
    -0.69
    /+
    -0.69
    /=
    -0.69
    /@
    -0.64
    VIAF
    -0.63
     enfati
    -0.62
     confronti
    -0.62
    ​​​​
    -0.62
    POSITIVE LOGITS
    ,—
    0.52
    Oo
    0.52
    mybatisplus
    0.51
    theilung
    0.50
     ditto
    0.49
     lately
    0.49
    ditto
    0.48
    mapStateToProps
    0.47
    .—
    0.46
    StackNavigator
    0.46
    Activations Density 0.308%

    No Known Activations