© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1300
    Prev
    Next
    INDEX
    Explanations

    references to the word "them" in various contexts

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

    mentions of items being referenced or discussed

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

    actions with them

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     its
    -0.74
    its
    -0.71
    Its
    -0.58
     Its
    -0.53
     itſelf
    -0.53
     eorum
    -0.53
    cluye
    -0.51
     kteří
    -0.50
    એ
    -0.50
     "..\..\..\
    -0.48
    POSITIVE LOGITS
    WebVitals
    0.74
    Obrázky
    0.73
    Autoritní
    0.73
     ones
    0.69
     bezeichneter
    0.68
     <<<<<<<<<<<<<<
    0.67
    createStatement
    0.65
    Datuak
    0.63
    ioutil
    0.63
     protoimpl
    0.63
    Activations Density 0.045%

    No Known Activations