© 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. 15-GEMMASCOPE-RES-16K
    11. 12462
    Prev
    Next
    INDEX
    Explanations

    the presence of the letter "A" at the beginning of phrases or sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     encre
    -0.88
    principalTable
    -0.81
    etheless
    -0.80
     useAppContext
    -0.80
    ukone
    -0.76
    Aiheesta
    -0.76
     فريبيس
    -0.75
    ftagPool
    -0.75
     estime
    -0.74
    طلحات
    -0.74
    POSITIVE LOGITS
     A
    1.14
    A
    0.95
    А
    0.67
    getA
    0.67
     E
    0.67
     U
    0.66
     G
    0.66
     B
    0.65
     M
    0.63
     F
    0.63
    Activations Density 0.208%

    No Known Activations