© 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. 16-GEMMASCOPE-RES-16K
    11. 1254
    Prev
    Next
    INDEX
    Explanations

    phrases indicating human emotions and relationships

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

    preceding third-person plural verbs

    np_acts-logits-general · gemini-2.0-flash

    people performing actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.76
     متعلقه
    -0.57
    Datuak
    -0.57
    ValueStyle
    -0.55
    ResponseWriter
    -0.54
    存于互联网档案馆
    -0.54
     estekak
    -0.54
    UTELY
    -0.53
    脚注の使い方
    -0.53
     Numa
    -0.51
    POSITIVE LOGITS
     habet
    0.57
     appliquer
    0.54
     quæ
    0.53
     pratiquer
    0.49
     valgt
    0.48
    нти
    0.48
    reactstrap
    0.48
     nemlig
    0.47
    IList
    0.46
    InitVars
    0.46
    Activations Density 0.051%

    No Known Activations