Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 1247
    Prev
    Next
    INDEX
    Explanations

    themes related to social dynamics and power relations involving racial groups

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

    Following auxiliary verbs (can, ll, I, we, who, he, they, to)

    np_acts-logits-general · gemini-2.0-flash

    pronoun + verb

    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
     actionMode
    -0.42
    verse
    -0.42
    omir
    -0.41
    Ẳ
    -0.41
    Compre
    -0.40
    ardust
    -0.40
    Ro
    -0.40
    롤
    -0.39
     Mir
    -0.39
     Ro
    -0.38
    POSITIVE LOGITS
    TestingModule
    0.86
    mybatisplus
    0.82
     requesting
    0.81
     TestBed
    0.77
     request
    0.75
    TagMode
    0.73
     receiving
    0.73
     agradec
    0.73
     requests
    0.72
     nahilalakip
    0.71
    Activations Density 0.246%

    No Known Activations