© 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. 1-GEMMASCOPE-RES-16K
    11. 5878
    Prev
    Next
    INDEX
    Explanations

    the word "ang" and its variations, indicating focus on a specific term related to a context likely involving Asian culture or language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tikang
    -0.88
    BrowserModule
    -0.84
    TestBed
    -0.81
     TestBed
    -0.80
     ModelExpression
    -0.79
     Hift
    -0.77
     Monfieur
    -0.75
     Anſ
    -0.74
     fevere
    -0.72
    mybatisplus
    -0.71
    POSITIVE LOGITS
    ang
    2.07
    ANG
    1.45
    angs
    1.12
    angnya
    1.02
    angg
    0.78
    angen
    0.69
    yang
    0.63
    anged
    0.61
    ång
    0.60
    anging
    0.60
    Activations Density 0.043%

    No Known Activations